{ "schema": 1, "generated": "2026-10-10", "repo": "cslht11/awesome-computed-tomography", "source": "data/*.yaml", "counts": { "papers": 289, "toolkits": 43, "datasets": 34, "benchmarks": 19, "learning": 29, "peer_reviewed": 226, "preprints": 63, "year_min": 1976, "year_max": 2026 }, "topics": [ { "id": "survey", "name": "Surveys & Reviews", "desc": "Overview papers, tutorials and comparative studies.", "count": 16 }, { "id": "classical", "name": "Classical & Iterative Reconstruction", "desc": "Analytical (FBP/FDK) and iterative (SART/SIRT/CGLS) reconstruction, hand-crafted regularizers (TV, TGV, non-local).", "count": 36 }, { "id": "sparse-view", "name": "Sparse-View CT", "desc": "Reconstruction from a reduced number of projection angles.", "count": 72 }, { "id": "limited-angle", "name": "Limited-Angle Tomography", "desc": "Missing angular wedge, where the null space makes the problem severely ill-posed.", "count": 20 }, { "id": "low-dose", "name": "Low-Dose CT Denoising", "desc": "Noise suppression at reduced tube current, in image, projection or dual domain.", "count": 47 }, { "id": "metal-artifact", "name": "Metal Artifact Reduction", "desc": "Beam hardening, photon starvation and scatter caused by high-density implants.", "count": 19 }, { "id": "spectral", "name": "Spectral & Dual-Energy CT", "desc": "Multi-energy acquisition, material decomposition, photon-counting CT.", "count": 13 }, { "id": "cbct", "name": "Cone-Beam CT", "desc": "Circular, helical and non-standard CBCT geometries; on-board imaging.", "count": 53 }, { "id": "dynamic", "name": "Dynamic & 4D CT", "desc": "Time-resolved reconstruction, motion modelling, perfusion and cardiac CT.", "count": 16 }, { "id": "scatter", "name": "Scatter Correction", "desc": "Scatter estimation and removal, both hardware- and software-based.", "count": 11 }, { "id": "geometry", "name": "Geometry Calibration & Motion Compensation", "desc": "Geometric self-calibration, marker-free alignment, rigid and non-rigid motion correction.", "count": 23 }, { "id": "unrolling", "name": "Deep Unrolling & Model-Based Learning", "desc": "Learned iterative schemes that unroll a classical solver, with or without data consistency.", "count": 60 }, { "id": "self-supervised", "name": "Self-Supervised & Untrained Methods", "desc": "Training without paired data — deep image prior, noise2noise-style, unsupervised regularization.", "count": 28 }, { "id": "diffusion", "name": "Diffusion & Generative Priors", "desc": "Score-based and diffusion models used as priors or samplers for tomographic inversion.", "count": 51 }, { "id": "inr", "name": "Implicit Neural Representations", "desc": "Coordinate-based networks (INR / NeRF) that represent the volume itself as the unknown.", "count": 23 }, { "id": "gaussian", "name": "Gaussian Splatting", "desc": "Explicit Gaussian primitives as a differentiable tomographic representation.", "count": 25 }, { "id": "other", "name": "Other Topics", "desc": "Industrial NDT, phase-contrast, quantitative CT, reconstruction software and anything that does not fit above.", "count": 12 } ], "papers": [ { "id": "k-neas-scalable-multi-material-ct-reconstruction-using-neura", "title": "$K$-NeAS: Scalable Multi-Material CT Reconstruction Using Neural SDFs", "year": 2026, "venue": "Off-Grid Workshop", "preprint": false, "topics": [ "spectral" ], "links": { "paper": "https://arxiv.org/abs/2607.14415" }, "_q": "$k$-neas: scalable multi-material ct reconstruction using neural sdfs off-grid workshop spectral & dual-energy ct arxiv.org 2607.14415" }, { "id": "3d-field-of-junctions", "title": "3D Field of Junctions: A Noise-Robust, Training-Free Structural Prior for Volumetric Inverse Problems", "year": 2026, "venue": "ECCV", "preprint": false, "topics": [ "self-supervised", "sparse-view" ], "links": { "paper": "https://arxiv.org/abs/2603.02149", "code": "https://github.com/voilalab/3D-Field-of-Junctions" }, "_q": "3d field of junctions: a noise-robust, training-free structural prior for volumetric inverse problems eccv self-supervised & untrained methods sparse-view ct arxiv.org 2603.02149 github.com 3d-field-of-junctions" }, { "id": "active-view-selection-with-perturbed-gaussian-ensemble-for-t", "title": "Active View Selection with Perturbed Gaussian Ensemble for Tomographic Reconstruction", "year": 2026, "venue": "ECCV", "preprint": false, "topics": [ "gaussian", "geometry" ], "links": { "paper": "https://arxiv.org/abs/2603.06852" }, "_q": "active view selection with perturbed gaussian ensemble for tomographic reconstruction eccv gaussian splatting geometry calibration & motion compensation arxiv.org 2603.06852" }, { "id": "anatomy-preserving-unpaired-cone-beam-ct-refinement-for-imag", "title": "Anatomy-preserving unpaired cone-beam CT refinement for image-guided radiotherapy using pseudo-label guided diffusion", "year": 2026, "venue": null, "preprint": true, "topics": [ "diffusion", "cbct" ], "links": { "paper": "https://arxiv.org/abs/2610.06094" }, "_q": "anatomy-preserving unpaired cone-beam ct refinement for image-guided radiotherapy using pseudo-label guided diffusion preprint diffusion & generative priors cone-beam ct arxiv.org 2610.06094" }, { "id": "at-fulltilt", "title": "At FullTilt: Real-Time Open-Set 3D Macromolecule Detection Directly from Tilted 2D Projections", "year": 2026, "venue": "NeurIPS", "preprint": false, "topics": [ "other" ], "links": { "paper": "https://arxiv.org/abs/2604.10766" }, "_q": "at fulltilt: real-time open-set 3d macromolecule detection directly from tilted 2d projections neurips other topics arxiv.org 2604.10766" }, { "id": "balancing-efficiency-and-restoration-lightweight-mamba-based", "title": "Balancing Efficiency and Restoration: Lightweight Mamba-Based Model for CT Metal Artifact Reduction", "year": 2026, "venue": "TRPMS", "preprint": false, "topics": [ "metal-artifact" ], "links": { "paper": "https://arxiv.org/abs/2604.06622", "code": "https://github.com/RICKand-MORTY/MARMamba" }, "_q": "balancing efficiency and restoration: lightweight mamba-based model for ct metal artifact reduction trpms metal artifact reduction arxiv.org 2604.06622 github.com marmamba" }, { "id": "cbct-based-synthetic-ct-generation-using-conditional-flow-ma", "title": "CBCT-Based Synthetic CT Generation Using Conditional Flow Matching Model", "year": 2026, "venue": null, "preprint": true, "topics": [ "diffusion", "cbct" ], "links": { "paper": "https://arxiv.org/abs/2603.05796" }, "_q": "cbct-based synthetic ct generation using conditional flow matching model preprint diffusion & generative priors cone-beam ct arxiv.org 2603.05796" }, { "id": "cg-glore-a-conjugate-gradient-based-global-local-regularizat", "title": "CG-GLORE: A Conjugate Gradient-Based Global-Local Regularization Network for Sparse-View CT Reconstruction", "year": 2026, "venue": "BMVC", "preprint": false, "topics": [ "sparse-view", "unrolling" ], "links": { "paper": "https://arxiv.org/abs/2608.15246" }, "_q": "cg-glore: a conjugate gradient-based global-local regularization network for sparse-view ct reconstruction bmvc sparse-view ct deep unrolling & model-based learning arxiv.org 2608.15246" }, { "id": "complex-wavelet-based-sinogram-segmentation-for-metal-artifa", "title": "Complex Wavelet-Based Sinogram Segmentation for Metal Artifact Reduction in Cone-Beam CT", "year": 2026, "venue": "PMB", "preprint": false, "topics": [ "metal-artifact", "cbct", "classical" ], "links": { "paper": "https://arxiv.org/abs/2602.14315" }, "_q": "complex wavelet-based sinogram segmentation for metal artifact reduction in cone-beam ct pmb metal artifact reduction cone-beam ct classical & iterative reconstruction arxiv.org 2602.14315" }, { "id": "computed-tomography-reconstruction-algorithm-using-markov-ra", "title": "Computed Tomography Reconstruction Algorithm Using Markov Random Field Model", "year": 2026, "venue": "J. Phys. Soc. Jpn.", "preprint": false, "topics": [ "classical" ], "links": { "paper": "https://arxiv.org/abs/2605.11637" }, "_q": "computed tomography reconstruction algorithm using markov random field model j. phys. soc. jpn. classical & iterative reconstruction arxiv.org 2605.11637" }, { "id": "conditional-diffusion-for-3d-ct-volume-reconstruction-from-2", "title": "Conditional Diffusion for 3D CT Volume Reconstruction from 2D X-rays", "year": 2026, "venue": "BMVC", "preprint": false, "topics": [ "diffusion" ], "links": { "paper": "https://arxiv.org/abs/2603.26509", "code": "https://github.com/ai-med/AXON/" }, "_q": "conditional diffusion for 3d ct volume reconstruction from 2d x-rays bmvc diffusion & generative priors arxiv.org 2603.26509 github.com axon" }, { "id": "conditional-diffusion-posterior-alignment-for-sparse-view-ct", "title": "Conditional Diffusion Posterior Alignment for Sparse-View CT Reconstruction", "year": 2026, "venue": null, "preprint": true, "topics": [ "diffusion", "geometry", "sparse-view" ], "links": { "paper": "https://arxiv.org/abs/2604.21960" }, "_q": "conditional diffusion posterior alignment for sparse-view ct reconstruction preprint diffusion & generative priors geometry calibration & motion compensation sparse-view ct arxiv.org 2604.21960" }, { "id": "cone-beam-artifact-reduction-in-gamma-knife-cbct-images-usin", "title": "Cone-beam artifact reduction in Gamma Knife CBCT images using a line-arc-line scan trajectory", "year": 2026, "venue": null, "preprint": true, "topics": [ "geometry", "cbct" ], "links": { "paper": "https://arxiv.org/abs/2609.30169" }, "_q": "cone-beam artifact reduction in gamma knife cbct images using a line-arc-line scan trajectory preprint geometry calibration & motion compensation cone-beam ct arxiv.org 2609.30169" }, { "id": "cone-beam-ct-image-quality-enhancement-using-a-latent-diffus", "title": "Cone-Beam CT Image Quality Enhancement Using A Latent Diffusion Model Trained with Simulated CBCT Artifacts", "year": 2026, "venue": null, "preprint": true, "topics": [ "diffusion", "cbct" ], "links": { "paper": "https://arxiv.org/abs/2603.26014" }, "_q": "cone-beam ct image quality enhancement using a latent diffusion model trained with simulated cbct artifacts preprint diffusion & generative priors cone-beam ct arxiv.org 2603.26014" }, { "id": "continuity-driven-synergistic-diffusion-with-neural-priors-f", "title": "Continuity-driven Synergistic Diffusion with Neural Priors for Ultra-Sparse-View CBCT Reconstruction", "year": 2026, "venue": null, "preprint": true, "topics": [ "diffusion", "sparse-view", "cbct" ], "links": { "paper": "https://arxiv.org/abs/2602.07980" }, "_q": "continuity-driven synergistic diffusion with neural priors for ultra-sparse-view cbct reconstruction preprint diffusion & generative priors sparse-view ct cone-beam ct arxiv.org 2602.07980" }, { "id": "cross-distribution-diffusion-priors-driven-iterative-reconst", "title": "Cross-Distribution Diffusion Priors-Driven Iterative Reconstruction for Sparse-View CT", "year": 2026, "venue": "TMI", "preprint": false, "topics": [ "diffusion", "sparse-view", "classical" ], "links": { "paper": "https://arxiv.org/abs/2509.13576" }, "_q": "cross-distribution diffusion priors-driven iterative reconstruction for sparse-view ct tmi diffusion & generative priors sparse-view ct classical & iterative reconstruction arxiv.org 2509.13576" }, { "id": "cross-modal-guidance-for-fast-diffusion-based-computed-tomog", "title": "Cross-Modal Guidance for Fast Diffusion-Based Computed Tomography", "year": 2026, "venue": "ICASSP", "preprint": false, "topics": [ "diffusion" ], "links": { "paper": "https://arxiv.org/abs/2603.01253" }, "_q": "cross-modal guidance for fast diffusion-based computed tomography icassp diffusion & generative priors arxiv.org 2603.01253" }, { "id": "cryoderec", "title": "A Supervised Multi-task Framework for Joint cryo-ET Restoration Enabled by Generative Physical Simulation", "year": 2026, "venue": "CVPR", "preprint": false, "topics": [ "limited-angle", "other" ], "links": { "paper": "https://openaccess.thecvf.com/content/CVPR2026/html/Wang_A_Supervised_Multi-task_Framework_for_Joint_cryo-ET_Restoration_Enabled_by_CVPR_2026_paper.html", "code": "https://github.com/ZhidongYang/CryoDeRec" }, "abbr": "CryoDeRec", "_q": "a supervised multi-task framework for joint cryo-et restoration enabled by generative physical simulation cryoderec cvpr limited-angle tomography other topics openaccess.thecvf.com wang_a_supervised_multi-task_framework_for_joint_cryo-et_restoration_enabled_by_cvpr_2026_paper.html github.com cryoderec" }, { "id": "diffnr-diffusion-enhanced-neural-representation-optimization", "title": "DiffNR: Diffusion-Enhanced Neural Representation Optimization for Sparse-View 3D Tomographic Reconstruction", "year": 2026, "venue": "AAAI", "preprint": false, "topics": [ "inr", "diffusion", "sparse-view" ], "links": { "paper": "https://arxiv.org/abs/2604.21518", "project": "https://ooonesevennn.github.io/DiffNR/" }, "_q": "diffnr: diffusion-enhanced neural representation optimization for sparse-view 3d tomographic reconstruction aaai implicit neural representations diffusion & generative priors sparse-view ct arxiv.org 2604.21518 ooonesevennn.github.io diffnr" }, { "id": "dinr", "title": "Regularizing INR with Diffusion Prior for Self-Supervised 3D Reconstruction of Neutron Computed Tomography Data", "year": 2026, "venue": "ICASSP", "preprint": false, "topics": [ "inr", "diffusion", "self-supervised" ], "links": { "paper": "https://arxiv.org/abs/2603.10947" }, "abbr": "DINR", "_q": "regularizing inr with diffusion prior for self-supervised 3d reconstruction of neutron computed tomography data dinr icassp implicit neural representations diffusion & generative priors self-supervised & untrained methods arxiv.org 2603.10947" }, { "id": "dm4ct", "title": "DM4CT: Benchmarking Diffusion Models for CT Reconstruction", "year": 2026, "venue": "ICLR", "preprint": false, "topics": [ "diffusion", "survey" ], "links": { "paper": "https://arxiv.org/abs/2602.18589", "code": "https://github.com/DM4CT/DM4CT" }, "abbr": "DM4CT", "_q": "dm4ct: benchmarking diffusion models for ct reconstruction dm4ct iclr diffusion & generative priors surveys & reviews arxiv.org 2602.18589 github.com dm4ct" }, { "id": "dose-aware-cold-diffusion-with-physics-consistency-for-gener", "title": "Dose-Aware Cold Diffusion with Physics Consistency for Generalizable Low-Dose CT Reconstruction", "year": 2026, "venue": "IJCNN", "preprint": false, "topics": [ "diffusion", "low-dose", "unrolling" ], "links": { "paper": "https://arxiv.org/abs/2609.18943" }, "_q": "dose-aware cold diffusion with physics consistency for generalizable low-dose ct reconstruction ijcnn diffusion & generative priors low-dose ct denoising deep unrolling & model-based learning arxiv.org 2609.18943" }, { "id": "dual-domain-u-nets-with-embedded-back-projection-operators-f", "title": "Dual-domain U-Nets with embedded back projection operators for motion-resolved 4D CBCT reconstruction", "year": 2026, "venue": null, "preprint": true, "topics": [ "dynamic", "cbct", "unrolling" ], "links": { "paper": "https://arxiv.org/abs/2608.03430" }, "_q": "dual-domain u-nets with embedded back projection operators for motion-resolved 4d cbct reconstruction preprint dynamic & 4d ct cone-beam ct deep unrolling & model-based learning arxiv.org 2608.03430" }, { "id": "dynamic-black-hole-emission-tomography", "title": "Dynamic Black-hole Emission Tomography with Physics-Informed Neural Fields", "year": 2026, "venue": "CVPR", "preprint": false, "topics": [ "inr", "dynamic", "other" ], "links": { "paper": "https://arxiv.org/abs/2602.08029" }, "_q": "dynamic black-hole emission tomography with physics-informed neural fields cvpr implicit neural representations dynamic & 4d ct other topics arxiv.org 2602.08029" }, { "id": "efficient-unrolled-networks", "title": "Efficient Unrolled Networks for Large-Scale 3D Inverse Problems", "year": 2026, "venue": "CVPR", "preprint": false, "topics": [ "unrolling", "sparse-view" ], "links": { "paper": "https://arxiv.org/abs/2601.02141", "code": "https://github.com/romainvo/efficient-unrolling" }, "_q": "efficient unrolled networks for large-scale 3d inverse problems cvpr deep unrolling & model-based learning sparse-view ct arxiv.org 2601.02141 github.com efficient-unrolling" }, { "id": "equivariance2inverse-a-practical-self-supervised-ct-reconstr", "title": "Equivariance2Inverse: A Practical Self-Supervised CT Reconstruction Method Benchmarked on Real, Limited-Angle, and Blurred Data", "year": 2026, "venue": "TCI", "preprint": false, "topics": [ "limited-angle", "self-supervised" ], "links": { "paper": "https://arxiv.org/abs/2510.23317" }, "_q": "equivariance2inverse: a practical self-supervised ct reconstruction method benchmarked on real, limited-angle, and blurred data tci limited-angle tomography self-supervised & untrained methods arxiv.org 2510.23317" }, { "id": "event-based-bos-tomography", "title": "Event-Based Sparse-View Background-Oriented Schlieren Tomography", "year": 2026, "venue": "ECCV", "preprint": false, "topics": [ "sparse-view", "other" ], "links": { "paper": "https://doi.org/10.1007/978-3-032-37335-9_18" }, "_q": "event-based sparse-view background-oriented schlieren tomography eccv sparse-view ct other topics doi.org 978-3-032-37335-9_18" }, { "id": "exact-gs", "title": "Exact-GS: Mathematically Rigorous and Accurate 3D Gaussian Splatting for 3D X-Ray Reconstruction", "year": 2026, "venue": "CVPR", "preprint": false, "topics": [ "gaussian", "geometry" ], "links": { "paper": "https://openaccess.thecvf.com/content/CVPR2026/html/Yang_Exact-GS_Mathematically_Rigorous_and_Accurate_3D_Gaussian_Splatting_for_3D_CVPR_2026_paper.html", "code": "https://github.com/brucee1323/Exact-GS" }, "abbr": "Exact-GS", "_q": "exact-gs: mathematically rigorous and accurate 3d gaussian splatting for 3d x-ray reconstruction exact-gs cvpr gaussian splatting geometry calibration & motion compensation openaccess.thecvf.com yang_exact-gs_mathematically_rigorous_and_accurate_3d_gaussian_splatting_for_3d_cvpr_2026_paper.html github.com exact-gs" }, { "id": "fact-gs-fast-and-scalable-ct-reconstruction-with-gaussian-sp", "title": "FaCT-GS: Fast and Scalable CT Reconstruction with Gaussian Splatting", "year": 2026, "venue": "ECCV", "preprint": false, "topics": [ "gaussian" ], "links": { "paper": "https://arxiv.org/abs/2604.01844", "code": "https://github.com/PaPieta/fact-gs" }, "_q": "fact-gs: fast and scalable ct reconstruction with gaussian splatting eccv gaussian splatting arxiv.org 2604.01844 github.com fact-gs" }, { "id": "field-of-view-extension-in-dental-cone-beam-ct-via-implicit-", "title": "Field-of-View Extension in Dental Cone-Beam CT via Implicit Neural Representations and Diffusion Model-Based Refinement", "year": 2026, "venue": "MICAD", "preprint": false, "topics": [ "inr", "diffusion", "cbct" ], "links": { "paper": "https://arxiv.org/abs/2609.28110", "code": "https://github.com/SusanneSchaub/CBCT-FOV-Extension" }, "_q": "field-of-view extension in dental cone-beam ct via implicit neural representations and diffusion model-based refinement micad implicit neural representations diffusion & generative priors cone-beam ct arxiv.org 2609.28110 github.com cbct-fov-extension" }, { "id": "foundation-vae", "title": "Foundation VAEs for 3D CT Reconstruction, Augmentation, and Generation", "year": 2026, "venue": "ICML", "preprint": false, "topics": [ "low-dose", "diffusion" ], "links": { "paper": "https://arxiv.org/abs/2605.30893", "code": "https://github.com/qic999/Foundation-VAE" }, "abbr": "Foundation-VAE", "_q": "foundation vaes for 3d ct reconstruction, augmentation, and generation foundation-vae icml low-dose ct denoising diffusion & generative priors arxiv.org 2605.30893 github.com foundation-vae" }, { "id": "from-sparse-x-rays-to-3d-ct-training-free-reconstruction-wit", "title": "From Sparse X-rays to 3D CT: Training-Free Reconstruction with Diffusion Priors", "year": 2026, "venue": "DGM4MICCAI", "preprint": false, "topics": [ "diffusion", "sparse-view", "self-supervised" ], "links": { "paper": "https://arxiv.org/abs/2606.20763", "code": "https://github.com/Fredy-Zhang/TF-PRDiT" }, "_q": "from sparse x-rays to 3d ct: training-free reconstruction with diffusion priors dgm4miccai diffusion & generative priors sparse-view ct self-supervised & untrained methods arxiv.org 2606.20763 github.com tf-prdit" }, { "id": "gb-svfbp-gaussian-based-shift-variant-fbp-neural-network", "title": "GB-SVFBP: Gaussian-Based Shift-Variant FBP neural network", "year": 2026, "venue": null, "preprint": true, "topics": [ "gaussian", "geometry", "unrolling" ], "links": { "paper": "https://arxiv.org/abs/2607.11584" }, "_q": "gb-svfbp: gaussian-based shift-variant fbp neural network preprint gaussian splatting geometry calibration & motion compensation deep unrolling & model-based learning arxiv.org 2607.11584" }, { "id": "geometry-aware-diffusion-approximate-posterior-sampling-for-", "title": "Geometry-Aware Diffusion Approximate Posterior Sampling for Sparse-View and Limited-Angle CT", "year": 2026, "venue": null, "preprint": true, "topics": [ "diffusion", "geometry", "limited-angle" ], "links": { "paper": "https://arxiv.org/abs/2610.08866" }, "_q": "geometry-aware diffusion approximate posterior sampling for sparse-view and limited-angle ct preprint diffusion & generative priors geometry calibration & motion compensation limited-angle tomography arxiv.org 2610.08866" }, { "id": "gh-naf", "title": "GH-NAF: Grid-Adaptive Hash-Level-Attended Neural Attenuation Fields for Discrepancy-Aware CBCT", "year": 2026, "venue": "CVPR", "preprint": false, "topics": [ "inr", "cbct" ], "links": { "paper": "https://openaccess.thecvf.com/content/CVPR2026/html/Oh_GH-NAF_Grid-Adaptive_Hash-Level-Attended_Neural_Attenuation_Fields_for_Discrepancy-Aware_CBCT_CVPR_2026_paper.html", "code": "https://github.com/seongje-oh/GH-NAF" }, "abbr": "GH-NAF", "_q": "gh-naf: grid-adaptive hash-level-attended neural attenuation fields for discrepancy-aware cbct gh-naf cvpr implicit neural representations cone-beam ct openaccess.thecvf.com oh_gh-naf_grid-adaptive_hash-level-attended_neural_attenuation_fields_for_discrepancy-aware_cbct_cvpr_2026_paper.html github.com gh-naf" }, { "id": "gr-gaussian", "title": "GR-Gaussian: Graph-Based Radiative Gaussian Splatting for Sparse-View Tomography", "year": 2026, "venue": "TCI", "preprint": false, "topics": [ "gaussian", "sparse-view" ], "links": { "paper": "https://doi.org/10.1109/TCI.2026.3701585" }, "abbr": "GR-Gaussian", "_q": "gr-gaussian: graph-based radiative gaussian splatting for sparse-view tomography gr-gaussian tci gaussian splatting sparse-view ct doi.org tci.2026.3701585" }, { "id": "h3d-marnet-wavelet-guided-dual-path-learning-for-metal-artif", "title": "H3D-MarNet: Wavelet-Guided Dual-Path Learning for Metal Artifact Suppression and CT Modality Transformation for Radiotherapy Workflows", "year": 2026, "venue": "ICPR", "preprint": false, "topics": [ "metal-artifact", "cbct", "classical" ], "links": { "paper": "https://arxiv.org/abs/2605.12252" }, "_q": "h3d-marnet: wavelet-guided dual-path learning for metal artifact suppression and ct modality transformation for radiotherapy workflows icpr metal artifact reduction cone-beam ct classical & iterative reconstruction arxiv.org 2605.12252" }, { "id": "haru-net-hybrid-attention-residual-u-net-for-edge-preserving", "title": "HARU-Net: Hybrid Attention Residual U-Net for Edge-Preserving Denoising in Cone-Beam Computed Tomography", "year": 2026, "venue": null, "preprint": true, "topics": [ "low-dose", "cbct", "unrolling" ], "links": { "paper": "https://arxiv.org/abs/2602.22544" }, "_q": "haru-net: hybrid attention residual u-net for edge-preserving denoising in cone-beam computed tomography preprint low-dose ct denoising cone-beam ct deep unrolling & model-based learning arxiv.org 2602.22544" }, { "id": "high-fidelity-3d-tooth-reconstruction-by-fusing-intraoral-sc", "title": "High-Fidelity 3D Tooth Reconstruction by Fusing Intraoral Scans and CBCT Data via a Deep Implicit Representation", "year": 2026, "venue": "ISBI", "preprint": false, "topics": [ "cbct" ], "links": { "paper": "https://arxiv.org/abs/2601.15358" }, "_q": "high-fidelity 3d tooth reconstruction by fusing intraoral scans and cbct data via a deep implicit representation isbi cone-beam ct arxiv.org 2601.15358" }, { "id": "ilv-iterative-latent-volumes-for-fast-and-accurate-sparse-vi", "title": "ILV: Iterative Latent Volumes for Fast and Accurate Sparse-View CT Reconstruction", "year": 2026, "venue": null, "preprint": true, "topics": [ "sparse-view" ], "links": { "paper": "https://arxiv.org/abs/2603.14915", "project": "https://sngryonglee.github.io/ILV/" }, "_q": "ilv: iterative latent volumes for fast and accurate sparse-view ct reconstruction preprint sparse-view ct arxiv.org 2603.14915 sngryonglee.github.io ilv" }, { "id": "integration-of-spectral-ct-with-pet-and-spect-bringing-tissu", "title": "Integration of Spectral CT with PET and SPECT: Bringing Tissue Composition Information to Molecular Imaging", "year": 2026, "venue": null, "preprint": true, "topics": [ "spectral" ], "links": { "paper": "https://arxiv.org/abs/2609.27398" }, "_q": "integration of spectral ct with pet and spect: bringing tissue composition information to molecular imaging preprint spectral & dual-energy ct arxiv.org 2609.27398" }, { "id": "iscs", "title": "Improving 2D Diffusion Models for 3D Medical Imaging with Inter-Slice Consistent Stochasticity", "year": 2026, "venue": "ICLR", "preprint": false, "topics": [ "diffusion", "sparse-view" ], "links": { "paper": "https://arxiv.org/abs/2602.04162", "code": "https://github.com/duchenhe/ISCS" }, "abbr": "ISCS", "_q": "improving 2d diffusion models for 3d medical imaging with inter-slice consistent stochasticity iscs iclr diffusion & generative priors sparse-view ct arxiv.org 2602.04162 github.com iscs" }, { "id": "joint-decoupled-iterative-cbct-reconstruction-with-hybrid-sc", "title": "Joint-decoupled iterative CBCT reconstruction with hybrid scatter estimation and voxel-adaptive beam hardening correction", "year": 2026, "venue": null, "preprint": true, "topics": [ "scatter", "cbct" ], "links": { "paper": "https://arxiv.org/abs/2607.15812" }, "_q": "joint-decoupled iterative cbct reconstruction with hybrid scatter estimation and voxel-adaptive beam hardening correction preprint scatter correction cone-beam ct arxiv.org 2607.15812" }, { "id": "klip", "title": "KLIP: Localized Distribution Shift Detection via KL-Divergence with Diffusion Priors in Inverse Problems", "year": 2026, "venue": "CVPR", "preprint": false, "topics": [ "diffusion", "sparse-view" ], "links": { "paper": "https://arxiv.org/abs/2605.31596", "code": "https://github.com/voilalab/KLIP" }, "abbr": "KLIP", "_q": "klip: localized distribution shift detection via kl-divergence with diffusion priors in inverse problems klip cvpr diffusion & generative priors sparse-view ct arxiv.org 2605.31596 github.com klip" }, { "id": "learning-where-and-what-to-lift-for-bi-planar-x-ray-to-ct-re", "title": "Learning Where and What to Lift for Bi-planar X-ray-to-CT Reconstruction", "year": 2026, "venue": null, "preprint": true, "topics": [ "sparse-view", "unrolling" ], "links": { "paper": "https://arxiv.org/abs/2608.17255" }, "_q": "learning where and what to lift for bi-planar x-ray-to-ct reconstruction preprint sparse-view ct deep unrolling & model-based learning arxiv.org 2608.17255" }, { "id": "leveraging-image-editing-foundation-models-for-data-efficien", "title": "Leveraging Image Editing Foundation Models for Data-Efficient CT Metal Artifact Reduction", "year": 2026, "venue": "CVPRW", "preprint": false, "topics": [ "metal-artifact" ], "links": { "paper": "https://arxiv.org/abs/2604.05934", "code": "https://github.com/ahmetemirdagi/CT-EditMAR" }, "_q": "leveraging image editing foundation models for data-efficient ct metal artifact reduction cvprw metal artifact reduction arxiv.org 2604.05934 github.com ct-editmar" }, { "id": "low-level-dataset-distillation", "title": "Low-Level Dataset Distillation for Medical Image Enhancement", "year": 2026, "venue": "ECCV", "preprint": false, "topics": [ "low-dose" ], "links": { "paper": "https://arxiv.org/abs/2511.13106", "code": "https://github.com/xufz123/Med_LLDD" }, "_q": "low-level dataset distillation for medical image enhancement eccv low-dose ct denoising arxiv.org 2511.13106 github.com med_lldd" }, { "id": "lucid-learned-undersampling-adaptive-consistency-guided-infe", "title": "LUCID: Learned Undersampling-Adaptive Consistency-Guided Inference with Deterministic Flow Matching for Sparse-View CT Reconstruction", "year": 2026, "venue": null, "preprint": true, "topics": [ "diffusion", "sparse-view", "unrolling" ], "links": { "paper": "https://arxiv.org/abs/2606.16212" }, "_q": "lucid: learned undersampling-adaptive consistency-guided inference with deterministic flow matching for sparse-view ct reconstruction preprint diffusion & generative priors sparse-view ct deep unrolling & model-based learning arxiv.org 2606.16212" }, { "id": "medgmae", "title": "MedGMAE: Gaussian Masked Autoencoders for Medical Volumetric Representation Learning", "year": 2026, "venue": "ICLR", "preprint": false, "topics": [ "self-supervised", "gaussian" ], "links": { "paper": "https://openreview.net/forum?id=Z2XIRLv535", "code": "https://github.com/windrise/MedGMAE" }, "abbr": "MedGMAE", "_q": "medgmae: gaussian masked autoencoders for medical volumetric representation learning medgmae iclr self-supervised & untrained methods gaussian splatting openreview.net forum?id=z2xirl github.com medgmae" }, { "id": "mgmar-metal-guided-metal-artifact-reduction-for-x-ray-comput", "title": "MGMAR: Metal-Guided Metal Artifact Reduction for X-ray Computed Tomography", "year": 2026, "venue": null, "preprint": true, "topics": [ "metal-artifact" ], "links": { "paper": "https://arxiv.org/abs/2603.13447" }, "_q": "mgmar: metal-guided metal artifact reduction for x-ray computed tomography preprint metal artifact reduction arxiv.org 2603.13447" }, { "id": "nab", "title": "NAB: Neural Adaptive Binning for Sparse-View CT Reconstruction", "year": 2026, "venue": "ICLR", "preprint": false, "topics": [ "sparse-view", "inr" ], "links": { "paper": "https://arxiv.org/abs/2602.02356", "code": "https://github.com/Wangduo-Xie/NAB_CT_reconstruction" }, "abbr": "NAB", "_q": "nab: neural adaptive binning for sparse-view ct reconstruction nab iclr sparse-view ct implicit neural representations arxiv.org 2602.02356 github.com nab_ct_reconstruction" }, { "id": "neuromorphic-xray-ct", "title": "Neuromorphic X-Ray Computed Tomography", "year": 2026, "venue": "ECCV", "preprint": false, "topics": [ "other" ], "links": { "paper": "https://doi.org/10.1007/978-3-032-37577-3_8", "project": "https://wanghongjian98.github.io/projects/neuroxct/" }, "_q": "neuromorphic x-ray computed tomography eccv other topics doi.org 978-3-032-37577-3_8 wanghongjian98.github.io neuroxct" }, { "id": "ngps", "title": "NGPS: Structure-Preserving Self-Supervised Denoising via Neighbor-Guided Patch Sampling", "year": 2026, "venue": "ECCV", "preprint": false, "topics": [ "self-supervised", "cbct" ], "links": { "paper": "https://arxiv.org/abs/2606.23200", "code": "https://github.com/cv-cho/NGPS" }, "abbr": "NGPS", "_q": "ngps: structure-preserving self-supervised denoising via neighbor-guided patch sampling ngps eccv self-supervised & untrained methods cone-beam ct arxiv.org 2606.23200 github.com ngps" }, { "id": "non-circular-scan-trajectories-for-reducing-cone-beam-artifa", "title": "Non-circular scan trajectories for reducing cone-beam artifacts in Gamma Knife CBCT images: a simulation study", "year": 2026, "venue": null, "preprint": true, "topics": [ "cbct" ], "links": { "paper": "https://arxiv.org/abs/2609.28232" }, "_q": "non-circular scan trajectories for reducing cone-beam artifacts in gamma knife cbct images: a simulation study preprint cone-beam ct arxiv.org 2609.28232" }, { "id": "openpros", "title": "OpenPros: A Large-Scale Dataset for Limited View Prostate Ultrasound Computed Tomography", "year": 2026, "venue": "ICLR", "preprint": false, "topics": [ "limited-angle", "other" ], "links": { "paper": "https://arxiv.org/abs/2505.12261", "project": "https://open-pros.github.io/" }, "abbr": "OpenPros", "_q": "openpros: a large-scale dataset for limited view prostate ultrasound computed tomography openpros iclr limited-angle tomography other topics arxiv.org 2505.12261 open-pros.github.io" }, { "id": "dc-pnpdp", "title": "Plug-and-Play Diffusion Meets ADMM: Dual-Variable Coupling for Robust Medical Image Reconstruction", "year": 2026, "venue": "ICML", "preprint": false, "topics": [ "diffusion", "classical" ], "links": { "paper": "https://arxiv.org/abs/2602.23214", "code": "https://github.com/duchenhe/DC-PnPDP" }, "_q": "plug-and-play diffusion meets admm: dual-variable coupling for robust medical image reconstruction icml diffusion & generative priors classical & iterative reconstruction arxiv.org 2602.23214 github.com dc-pnpdp" }, { "id": "projection-volume-fidelity-divergence-diagnosing-and-control", "title": "Projection-Volume Fidelity Divergence: Diagnosing and Controlling Optimization Drift in Sparse-View 3D Gaussian Tomography", "year": 2026, "venue": null, "preprint": true, "topics": [ "gaussian", "sparse-view" ], "links": { "paper": "https://arxiv.org/abs/2606.22525" }, "_q": "projection-volume fidelity divergence: diagnosing and controlling optimization drift in sparse-view 3d gaussian tomography preprint gaussian splatting sparse-view ct arxiv.org 2606.22525" }, { "id": "radioactive-3d-gaussian-ray-tracing-for-tomographic-reconstr", "title": "Radioactive 3D Gaussian Ray Tracing for Tomographic Reconstruction", "year": 2026, "venue": null, "preprint": true, "topics": [ "gaussian" ], "links": { "paper": "https://arxiv.org/abs/2602.01057" }, "_q": "radioactive 3d gaussian ray tracing for tomographic reconstruction preprint gaussian splatting arxiv.org 2602.01057" }, { "id": "ram", "title": "Reconstruct Anything Model: A Lightweight General Model for Computational Imaging", "year": 2026, "venue": "ICLR", "preprint": false, "topics": [ "unrolling" ], "links": { "paper": "https://arxiv.org/abs/2503.08915", "code": "https://github.com/matthieutrs/ram" }, "abbr": "RAM", "_q": "reconstruct anything model: a lightweight general model for computational imaging ram iclr deep unrolling & model-based learning arxiv.org 2503.08915 github.com ram" }, { "id": "revisiting-pose-sensitivity-in-splat-based-computed-tomograp", "title": "Revisiting Pose Sensitivity in Splat-based Computed Tomography under Sparse-view Reconstruction", "year": 2026, "venue": "CVPR", "preprint": false, "topics": [ "gaussian", "geometry", "sparse-view" ], "links": { "paper": "https://arxiv.org/abs/2608.04752" }, "_q": "revisiting pose sensitivity in splat-based computed tomography under sparse-view reconstruction cvpr gaussian splatting geometry calibration & motion compensation sparse-view ct arxiv.org 2608.04752" }, { "id": "riner", "title": "Unsupervised Multi-Parameter Inverse Solving for Reducing Ring Artifacts in 3D X-Ray CBCT", "year": 2026, "venue": "AAAI", "preprint": false, "topics": [ "cbct", "geometry" ], "links": { "paper": "https://arxiv.org/abs/2412.05853", "code": "https://github.com/iwuqing/Riner" }, "abbr": "Riner", "_q": "unsupervised multi-parameter inverse solving for reducing ring artifacts in 3d x-ray cbct riner aaai cone-beam ct geometry calibration & motion compensation arxiv.org 2412.05853 github.com riner" }, { "id": "robustness-and-stability-analysis-of-differentiable-shift-va", "title": "Robustness and Stability Analysis of Differentiable Shift-Variant FBP for Cone-Beam CT under Challenging Acquisition Settings", "year": 2026, "venue": "MELBA", "preprint": false, "topics": [ "geometry", "cbct", "classical" ], "links": { "paper": "https://arxiv.org/abs/2607.09828", "project": "https://melba-journal.org/2026:014" }, "_q": "robustness and stability analysis of differentiable shift-variant fbp for cone-beam ct under challenging acquisition settings melba geometry calibration & motion compensation cone-beam ct classical & iterative reconstruction arxiv.org 2607.09828 melba-journal.org 2026:014" }, { "id": "shape-guided-gaussian-splatting-for-sparse-view-x-ray-3d-rec", "title": "Shape-guided Gaussian Splatting for Sparse-View X-ray 3D Reconstruction", "year": 2026, "venue": null, "preprint": true, "topics": [ "gaussian", "sparse-view" ], "links": { "paper": "https://arxiv.org/abs/2609.10376", "code": "https://github.com/polyshape-lab/ShapeGuidedGaussian" }, "_q": "shape-guided gaussian splatting for sparse-view x-ray 3d reconstruction preprint gaussian splatting sparse-view ct arxiv.org 2609.10376 github.com shapeguidedgaussian" }, { "id": "spectral-consistent-flow", "title": "Spectral Consistent Flow for One-Step 3D Medical Image Translation", "year": 2026, "venue": "ECCV", "preprint": false, "topics": [ "diffusion", "cbct" ], "links": { "paper": "https://arxiv.org/abs/2607.10627" }, "_q": "spectral consistent flow for one-step 3d medical image translation eccv diffusion & generative priors cone-beam ct arxiv.org 2607.10627" }, { "id": "splat-based-metal-artifact-reduction-in-cone-beam-ct-via-com", "title": "Splat-Based Metal Artifact Reduction in Cone-Beam CT via Compact Attenuation Modeling", "year": 2026, "venue": "CVPR", "preprint": false, "topics": [ "gaussian", "metal-artifact", "cbct" ], "links": { "paper": "https://arxiv.org/abs/2608.04764" }, "_q": "splat-based metal artifact reduction in cone-beam ct via compact attenuation modeling cvpr gaussian splatting metal artifact reduction cone-beam ct arxiv.org 2608.04764" }, { "id": "splat-based-metal-artifact-reduction-in-cone-beam-ct-via-pol", "title": "Splat-based Metal Artifact Reduction in Cone-Beam CT via Polychromatic Modeling", "year": 2026, "venue": "CGF", "preprint": false, "topics": [ "gaussian", "metal-artifact", "cbct" ], "links": { "paper": "https://arxiv.org/abs/2608.13159" }, "_q": "splat-based metal artifact reduction in cone-beam ct via polychromatic modeling cgf gaussian splatting metal artifact reduction cone-beam ct arxiv.org 2608.13159" }, { "id": "texture-preserving-implicit-neural-representation-for-cone-b", "title": "Texture-preserving implicit neural representation for Cone beam CT truncated reconstruction", "year": 2026, "venue": null, "preprint": true, "topics": [ "inr", "geometry", "cbct" ], "links": { "paper": "https://arxiv.org/abs/2606.06039" }, "_q": "texture-preserving implicit neural representation for cone beam ct truncated reconstruction preprint implicit neural representations geometry calibration & motion compensation cone-beam ct arxiv.org 2606.06039" }, { "id": "tg-field-geometry-aware-radiative-gaussian-fields-for-tomogr", "title": "TG-Field: Geometry-Aware Radiative Gaussian Fields for Tomographic Reconstruction", "year": 2026, "venue": "AAAI", "preprint": false, "topics": [ "gaussian", "geometry" ], "links": { "paper": "https://arxiv.org/abs/2602.11705" }, "_q": "tg-field: geometry-aware radiative gaussian fields for tomographic reconstruction aaai gaussian splatting geometry calibration & motion compensation arxiv.org 2602.11705" }, { "id": "toward-a-foundation-plug-and-play-prior-for-computed-tomogra", "title": "Toward a Foundation Plug-and-Play Prior for Computed Tomography Reconstruction via a Multimodal Diffusion Model", "year": 2026, "venue": "SC Workshops", "preprint": false, "topics": [ "diffusion", "unrolling" ], "links": { "paper": "https://arxiv.org/abs/2608.23190" }, "_q": "toward a foundation plug-and-play prior for computed tomography reconstruction via a multimodal diffusion model sc workshops diffusion & generative priors deep unrolling & model-based learning arxiv.org 2608.23190" }, { "id": "toward-ct-equivalent-image-quality-in-low-dose-radiotherapy-", "title": "Toward CT-Equivalent Image Quality in Low-Dose Radiotherapy Planning: Conditional Diffusion-Based CBCT-to-CT Synthesis and the Impact of CBCT Input Representation", "year": 2026, "venue": null, "preprint": true, "topics": [ "diffusion", "low-dose", "cbct" ], "links": { "paper": "https://arxiv.org/abs/2608.08919" }, "_q": "toward ct-equivalent image quality in low-dose radiotherapy planning: conditional diffusion-based cbct-to-ct synthesis and the impact of cbct input representation preprint diffusion & generative priors low-dose ct denoising cone-beam ct arxiv.org 2608.08919" }, { "id": "towards-reconstructing-experimental-sparse-view-x-ray-ct-dat", "title": "Towards reconstructing experimental sparse-view X-ray CT data with diffusion models", "year": 2026, "venue": null, "preprint": true, "topics": [ "diffusion", "sparse-view" ], "links": { "paper": "https://arxiv.org/abs/2602.12755" }, "_q": "towards reconstructing experimental sparse-view x-ray ct data with diffusion models preprint diffusion & generative priors sparse-view ct arxiv.org 2602.12755" }, { "id": "unsupervised-metal-artifact-reduction-in-dental-cbct-using-f", "title": "Unsupervised Metal Artifact Reduction in Dental CBCT using Fine-tuned Cycle-Consistent Adversarial Networks", "year": 2026, "venue": "Digital", "preprint": false, "topics": [ "metal-artifact", "self-supervised", "cbct" ], "links": { "paper": "https://arxiv.org/abs/2607.20977" }, "_q": "unsupervised metal artifact reduction in dental cbct using fine-tuned cycle-consistent adversarial networks digital metal artifact reduction self-supervised & untrained methods cone-beam ct arxiv.org 2607.20977" }, { "id": "variational-garrote", "title": "Variational Garrote for Sparse Inverse Problems", "year": 2026, "venue": "J. Comput. Sci.", "preprint": false, "topics": [ "classical", "sparse-view" ], "links": { "paper": "https://doi.org/10.1016/j.jocs.2026.102980" }, "_q": "variational garrote for sparse inverse problems j. comput. sci. classical & iterative reconstruction sparse-view ct doi.org j.jocs.2026.102980" }, { "id": "vodasure", "title": "VoDaSuRe: A Large-Scale Dataset Revealing Domain Shift in Volumetric Super-Resolution", "year": 2026, "venue": "CVPR", "preprint": false, "topics": [ "other" ], "links": { "paper": "https://arxiv.org/abs/2603.23153", "project": "https://augusthoeg.github.io/VoDaSuRe/" }, "abbr": "VoDaSuRe", "_q": "vodasure: a large-scale dataset revealing domain shift in volumetric super-resolution vodasure cvpr other topics arxiv.org 2603.23153 augusthoeg.github.io vodasure" }, { "id": "voxelsynth3d-interpretable-volumetric-image-domain-metal-art", "title": "VoxelSynth3D: Interpretable Volumetric Image-Domain Metal Artifact Reduction with a Paired Synthetic CLINIC-Metal Benchmark", "year": 2026, "venue": "BHI", "preprint": false, "topics": [ "metal-artifact" ], "links": { "paper": "https://arxiv.org/abs/2610.01512" }, "_q": "voxelsynth3d: interpretable volumetric image-domain metal artifact reduction with a paired synthetic clinic-metal benchmark bhi metal artifact reduction arxiv.org 2610.01512" }, { "id": "xden-1k", "title": "XDen-1K: A Density Field Dataset of Real-World Objects", "year": 2026, "venue": "ECCV", "preprint": false, "topics": [ "sparse-view", "other" ], "links": { "paper": "https://arxiv.org/abs/2512.10668" }, "abbr": "XDen-1K", "_q": "xden-1k: a density field dataset of real-world objects xden-1k eccv sparse-view ct other topics arxiv.org 2512.10668" }, { "id": "3d-cbct-artefact-removal-using-perpendicular-score-based-dif", "title": "3D CBCT Artefact Removal Using Perpendicular Score-Based Diffusion Models", "year": 2025, "venue": "DGM4MICCAI", "preprint": false, "topics": [ "diffusion", "cbct" ], "links": { "paper": "https://arxiv.org/abs/2603.06300" }, "_q": "3d cbct artefact removal using perpendicular score-based diffusion models dgm4miccai diffusion & generative priors cone-beam ct arxiv.org 2603.06300" }, { "id": "4dgs-4dcbct", "title": "Spatiotemporal Gaussian Optimization for 4D Cone Beam CT Reconstruction from Sparsely Sampled Projections", "year": 2025, "venue": null, "preprint": true, "topics": [ "gaussian", "dynamic", "cbct" ], "links": { "paper": "https://arxiv.org/abs/2501.04140", "code": "https://github.com/fuyabo/4DGS_for_4DCBCT" }, "abbr": "4DGS-4DCBCT", "_q": "spatiotemporal gaussian optimization for 4d cone beam ct reconstruction from sparsely sampled projections 4dgs-4dcbct preprint gaussian splatting dynamic & 4d ct cone-beam ct arxiv.org 2501.04140 github.com 4dgs_for_4dcbct" }, { "id": "a-ct-geometry-with-multiple-centers-of-rotation-for-solving-", "title": "A CT Geometry With Multiple Centers Of Rotation For Solving Sparse View Problem", "year": 2025, "venue": null, "preprint": true, "topics": [ "geometry", "sparse-view" ], "links": { "paper": "https://arxiv.org/abs/2502.06125" }, "_q": "a ct geometry with multiple centers of rotation for solving sparse view problem preprint geometry calibration & motion compensation sparse-view ct arxiv.org 2502.06125" }, { "id": "a-learnt-half-quadratic-splitting-based-algorithm-for-fast-a", "title": "A Learnt Half-Quadratic Splitting-Based Algorithm for Fast and High-Quality Industrial Cone-beam CT Reconstruction", "year": 2025, "venue": null, "preprint": true, "topics": [ "cbct", "unrolling" ], "links": { "paper": "https://arxiv.org/abs/2501.13128" }, "_q": "a learnt half-quadratic splitting-based algorithm for fast and high-quality industrial cone-beam ct reconstruction preprint cone-beam ct deep unrolling & model-based learning arxiv.org 2501.13128" }, { "id": "accelerated-optimization-of-implicit-neural-representations-", "title": "Accelerated Optimization of Implicit Neural Representations for CT Reconstruction", "year": 2025, "venue": null, "preprint": true, "topics": [ "inr" ], "links": { "paper": "https://arxiv.org/abs/2504.13390" }, "_q": "accelerated optimization of implicit neural representations for ct reconstruction preprint implicit neural representations arxiv.org 2504.13390" }, { "id": "adaptive-diffusion-models-for-sparse-view-motion-corrected-h", "title": "Adaptive Diffusion Models for Sparse-View Motion-Corrected Head Cone-beam CT", "year": 2025, "venue": "TRPMS", "preprint": false, "topics": [ "diffusion", "sparse-view", "cbct" ], "links": { "paper": "https://arxiv.org/abs/2504.14033", "project": "https://antoinedepaepe.github.io/jrm-adm-io/" }, "_q": "adaptive diffusion models for sparse-view motion-corrected head cone-beam ct trpms diffusion & generative priors sparse-view ct cone-beam ct arxiv.org 2504.14033 antoinedepaepe.github.io jrm-adm-io" }, { "id": "advancing-limited-angle-ct-reconstruction-through-diffusion-", "title": "Advancing Limited-Angle CT Reconstruction Through Diffusion-Based Sinogram Completion", "year": 2025, "venue": "ICIP", "preprint": false, "topics": [ "diffusion", "limited-angle" ], "links": { "paper": "https://arxiv.org/abs/2505.19385" }, "_q": "advancing limited-angle ct reconstruction through diffusion-based sinogram completion icip diffusion & generative priors limited-angle tomography arxiv.org 2505.19385" }, { "id": "an-iterative-reconstruction-method-for-dental-cone-beam-comp", "title": "An Iterative Reconstruction Method for Dental Cone-Beam Computed Tomography with a Truncated Field of View", "year": 2025, "venue": null, "preprint": true, "topics": [ "geometry", "cbct", "classical" ], "links": { "paper": "https://arxiv.org/abs/2508.07618" }, "_q": "an iterative reconstruction method for dental cone-beam computed tomography with a truncated field of view preprint geometry calibration & motion compensation cone-beam ct classical & iterative reconstruction arxiv.org 2508.07618" }, { "id": "pixel-wise-metrics-reliability", "title": "Are Pixel-Wise Metrics Reliable for Sparse-View Computed Tomography Reconstruction?", "year": 2025, "venue": "NeurIPS", "preprint": false, "topics": [ "survey", "sparse-view" ], "links": { "paper": "https://arxiv.org/abs/2506.02093", "code": "https://github.com/MrGiovanni/CARE" }, "_q": "are pixel-wise metrics reliable for sparse-view computed tomography reconstruction? neurips surveys & reviews sparse-view ct arxiv.org 2506.02093 github.com care" }, { "id": "bigger-isn-t-always-better-towards-a-general-prior-for-medic", "title": "Bigger Isn't Always Better: Towards a General Prior for Medical Image Reconstruction", "year": 2025, "venue": "GCPR", "preprint": false, "topics": [ "diffusion" ], "links": { "paper": "https://arxiv.org/abs/2501.07376", "code": "https://github.com/VLOGroup/bigger-isnt-always-better" }, "_q": "bigger isn't always better: towards a general prior for medical image reconstruction gcpr diffusion & generative priors arxiv.org 2501.07376 github.com bigger-isnt-always-better" }, { "id": "coco-pnp", "title": "Learning Cocoercive Conservative Denoisers via Helmholtz Decomposition for Poisson Inverse Problems", "year": 2025, "venue": "NeurIPS", "preprint": false, "topics": [ "unrolling", "classical" ], "links": { "paper": "https://arxiv.org/abs/2505.08909", "code": "https://github.com/FizzzFizzz/CoCo-PnP" }, "abbr": "CoCo-PnP", "_q": "learning cocoercive conservative denoisers via helmholtz decomposition for poisson inverse problems coco-pnp neurips deep unrolling & model-based learning classical & iterative reconstruction arxiv.org 2505.08909 github.com coco-pnp" }, { "id": "coord-sos-pact", "title": "Coordinate-Based Speed of Sound Recovery for Aberration-Corrected Photoacoustic Computed Tomography", "year": 2025, "venue": "ICCV", "preprint": false, "topics": [ "inr", "other" ], "links": { "paper": "https://arxiv.org/abs/2409.10876", "project": "https://lukeli0425.github.io/Coord-SoS-PACT/" }, "_q": "coordinate-based speed of sound recovery for aberration-corrected photoacoustic computed tomography iccv implicit neural representations other topics arxiv.org 2409.10876 lukeli0425.github.io coord-sos-pact" }, { "id": "cvg-diff", "title": "Cross-View Generalized Diffusion Model for Sparse-View CT Reconstruction", "year": 2025, "venue": "MICCAI", "preprint": false, "topics": [ "sparse-view", "diffusion" ], "links": { "paper": "https://doi.org/10.1007/978-3-032-05325-1_14", "code": "https://github.com/xmed-lab/CvG-Diff" }, "abbr": "CvG-Diff", "_q": "cross-view generalized diffusion model for sparse-view ct reconstruction cvg-diff miccai sparse-view ct diffusion & generative priors doi.org 978-3-032-05325-1_14 github.com cvg-diff" }, { "id": "data-efficient-limited-angle-ct-using-deep-priors-and-regula", "title": "Data-Efficient Limited-Angle CT Using Deep Priors and Regularization", "year": 2025, "venue": null, "preprint": true, "topics": [ "limited-angle", "unrolling" ], "links": { "paper": "https://arxiv.org/abs/2502.12293" }, "_q": "data-efficient limited-angle ct using deep priors and regularization preprint limited-angle tomography deep unrolling & model-based learning arxiv.org 2502.12293" }, { "id": "denomamba", "title": "DenoMamba: A Fused State-Space Model for Low-Dose CT Denoising", "year": 2025, "venue": "JBHI", "preprint": false, "topics": [ "low-dose" ], "links": { "paper": "https://doi.org/10.1109/jbhi.2025.3629034", "code": "https://github.com/icon-lab/DenoMamba" }, "abbr": "DenoMamba", "_q": "denomamba: a fused state-space model for low-dose ct denoising denomamba jbhi low-dose ct denoising doi.org jbhi.2025.3629034 github.com denomamba" }, { "id": "dgr", "title": "Discretized Gaussian Representation for Tomographic Reconstruction", "year": 2025, "venue": "ICCV", "preprint": false, "topics": [ "gaussian" ], "links": { "paper": "https://doi.org/10.1109/iccv51701.2025.02325", "code": "https://github.com/wskingdom/DGR" }, "abbr": "DGR", "_q": "discretized gaussian representation for tomographic reconstruction dgr iccv gaussian splatting doi.org iccv51701.2025.02325 github.com dgr" }, { "id": "diffnaf", "title": "Iterative Diffusion-Refined Neural Attenuation Fields for Multi-Source Stationary Tomography", "year": 2025, "venue": null, "preprint": true, "topics": [ "inr", "diffusion" ], "links": { "paper": "https://arxiv.org/abs/2511.14310" }, "abbr": "DiffNAF", "_q": "iterative diffusion-refined neural attenuation fields for multi-source stationary tomography diffnaf preprint implicit neural representations diffusion & generative priors arxiv.org 2511.14310" }, { "id": "diffusion-based-limited-angle-ct-reconstruction-under-noisy-", "title": "Diffusion-Based Limited-Angle CT Reconstruction under Noisy Conditions", "year": 2025, "venue": "ICIP", "preprint": false, "topics": [ "diffusion", "limited-angle" ], "links": { "paper": "https://arxiv.org/abs/2507.05647" }, "_q": "diffusion-based limited-angle ct reconstruction under noisy conditions icip diffusion & generative priors limited-angle tomography arxiv.org 2507.05647" }, { "id": "digs-dynamic-cbct-reconstruction-using-deformation-informed-", "title": "DIGS: Dynamic CBCT Reconstruction using Deformation-Informed 4D Gaussian Splatting and a Low-Rank Free-Form Deformation Model", "year": 2025, "venue": "MICCAI", "preprint": false, "topics": [ "gaussian", "dynamic", "cbct" ], "links": { "paper": "https://arxiv.org/abs/2506.22280", "code": "https://github.com/Yuliang-Huang/DIGS" }, "_q": "digs: dynamic cbct reconstruction using deformation-informed 4d gaussian splatting and a low-rank free-form deformation model miccai gaussian splatting dynamic & 4d ct cone-beam ct arxiv.org 2506.22280 github.com digs" }, { "id": "dvg-diffusion-dual-view-guided-diffusion-model-for-ct-recons", "title": "DVG-Diffusion: Dual-View Guided Diffusion Model for CT Reconstruction from X-Rays", "year": 2025, "venue": null, "preprint": true, "topics": [ "diffusion" ], "links": { "paper": "https://arxiv.org/abs/2503.17804" }, "_q": "dvg-diffusion: dual-view guided diffusion model for ct reconstruction from x-rays preprint diffusion & generative priors arxiv.org 2503.17804" }, { "id": "end-to-end-deep-learning-for-interior-tomography-with-low-do", "title": "End-to-End Deep Learning for Interior Tomography with Low-Dose X-ray CT", "year": 2025, "venue": "PMB", "preprint": false, "topics": [ "limited-angle", "low-dose", "unrolling" ], "links": { "paper": "https://arxiv.org/abs/2501.05085" }, "_q": "end-to-end deep learning for interior tomography with low-dose x-ray ct pmb limited-angle tomography low-dose ct denoising deep unrolling & model-based learning arxiv.org 2501.05085" }, { "id": "enhancing-synthetic-ct-from-cbct-via-multimodal-fusion-and-e", "title": "Enhancing Synthetic CT from CBCT via Multimodal Fusion and End-To-End Registration", "year": 2025, "venue": "CAIP", "preprint": false, "topics": [ "geometry", "cbct" ], "links": { "paper": "https://arxiv.org/abs/2507.06067" }, "_q": "enhancing synthetic ct from cbct via multimodal fusion and end-to-end registration caip geometry calibration & motion compensation cone-beam ct arxiv.org 2507.06067" }, { "id": "enhancing-synthetic-ct-from-cbct-via-multimodal-fusion-a-stu", "title": "Enhancing Synthetic CT from CBCT via Multimodal Fusion: A Study on the Impact of CBCT Quality and Alignment", "year": 2025, "venue": null, "preprint": true, "topics": [ "geometry", "cbct" ], "links": { "paper": "https://arxiv.org/abs/2506.08716" }, "_q": "enhancing synthetic ct from cbct via multimodal fusion: a study on the impact of cbct quality and alignment preprint geometry calibration & motion compensation cone-beam ct arxiv.org 2506.08716" }, { "id": "epi-naf", "title": "Epi-NAF: Enhancing Neural Attenuation Fields for Limited-Angle CT with Epipolar Consistency", "year": 2025, "venue": "ISBI", "preprint": false, "topics": [ "inr", "limited-angle", "geometry" ], "links": { "paper": "https://arxiv.org/abs/2411.06181" }, "abbr": "Epi-NAF", "_q": "epi-naf: enhancing neural attenuation fields for limited-angle ct with epipolar consistency epi-naf isbi implicit neural representations limited-angle tomography geometry calibration & motion compensation arxiv.org 2411.06181" }, { "id": "equivariant-conditional-diffusion-model-for-head-and-neck-ct", "title": "Equivariant Conditional Diffusion Model for Head and Neck CT Image Synthesis from CBCT", "year": 2025, "venue": "Med Phys", "preprint": false, "topics": [ "diffusion", "cbct" ], "links": { "paper": "https://arxiv.org/abs/2509.21913" }, "_q": "equivariant conditional diffusion model for head and neck ct image synthesis from cbct med phys diffusion & generative priors cone-beam ct arxiv.org 2509.21913" }, { "id": "equivariant-multiscale-learned-invertible-reconstruction-for", "title": "Equivariant Multiscale Learned Invertible Reconstruction for Cone Beam CT: From Simulated to Real Data", "year": 2025, "venue": null, "preprint": true, "topics": [ "cbct", "unrolling" ], "links": { "paper": "https://arxiv.org/abs/2512.21180" }, "_q": "equivariant multiscale learned invertible reconstruction for cone beam ct: from simulated to real data preprint cone-beam ct deep unrolling & model-based learning arxiv.org 2512.21180" }, { "id": "find-net-fourier-integrated-network-with-dictionary-kernels-", "title": "FIND-Net -- Fourier-Integrated Network with Dictionary Kernels for Metal Artifact Reduction", "year": 2025, "venue": "MICCAI", "preprint": false, "topics": [ "metal-artifact", "unrolling" ], "links": { "paper": "https://arxiv.org/abs/2508.10617", "code": "https://github.com/Farid-Tasharofi/FIND-Net" }, "_q": "find-net -- fourier-integrated network with dictionary kernels for metal artifact reduction miccai metal artifact reduction deep unrolling & model-based learning arxiv.org 2508.10617 github.com find-net" }, { "id": "ganext-a-fully-convnext-enhanced-generative-adversarial-netw", "title": "GANeXt: A Fully ConvNeXt-Enhanced Generative Adversarial Network for MRI- and CBCT-to-CT Synthesis", "year": 2025, "venue": null, "preprint": true, "topics": [ "diffusion", "cbct", "unrolling" ], "links": { "paper": "https://arxiv.org/abs/2512.19336" }, "_q": "ganext: a fully convnext-enhanced generative adversarial network for mri- and cbct-to-ct synthesis preprint diffusion & generative priors cone-beam ct deep unrolling & model-based learning arxiv.org 2512.19336" }, { "id": "glfc-unified-global-local-feature-and-contrast-learning-with", "title": "GLFC: Unified Global-Local Feature and Contrast Learning with Mamba-Enhanced UNet for Synthetic CT Generation from CBCT", "year": 2025, "venue": "ISBI", "preprint": false, "topics": [ "cbct" ], "links": { "paper": "https://arxiv.org/abs/2501.02992", "code": "https://github.com/HiLab-git/GLFC" }, "_q": "glfc: unified global-local feature and contrast learning with mamba-enhanced unet for synthetic ct generation from cbct isbi cone-beam ct arxiv.org 2501.02992 github.com glfc" }, { "id": "insideout-integrated-rgb-radiative-gaussian-splatting-for-co", "title": "InsideOut: Integrated RGB-Radiative Gaussian Splatting for Comprehensive 3D Object Representation", "year": 2025, "venue": "ICCV", "preprint": false, "topics": [ "gaussian" ], "links": { "paper": "https://arxiv.org/abs/2510.17864" }, "_q": "insideout: integrated rgb-radiative gaussian splatting for comprehensive 3d object representation iccv gaussian splatting arxiv.org 2510.17864" }, { "id": "latent-space-consistency-for-sparse-view-ct-reconstruction", "title": "Latent Space Consistency for Sparse-View CT Reconstruction", "year": 2025, "venue": null, "preprint": true, "topics": [ "sparse-view" ], "links": { "paper": "https://arxiv.org/abs/2507.11152" }, "_q": "latent space consistency for sparse-view ct reconstruction preprint sparse-view ct arxiv.org 2507.11152" }, { "id": "learning-wavelet-sparse-fdk-for-3d-cone-beam-ct-reconstructi", "title": "Learning Wavelet-Sparse FDK for 3D Cone-Beam CT Reconstruction", "year": 2025, "venue": "Fully3D", "preprint": false, "topics": [ "cbct", "classical" ], "links": { "paper": "https://arxiv.org/abs/2505.13579" }, "_q": "learning wavelet-sparse fdk for 3d cone-beam ct reconstruction fully3d cone-beam ct classical & iterative reconstruction arxiv.org 2505.13579" }, { "id": "limited-angle-cbct-reconstruction-via-geometry-integrated-cy", "title": "Limited-Angle CBCT Reconstruction via Geometry-Integrated Cycle-domain Denoising Diffusion Probabilistic Models", "year": 2025, "venue": null, "preprint": true, "topics": [ "diffusion", "geometry", "limited-angle" ], "links": { "paper": "https://arxiv.org/abs/2506.13545" }, "_q": "limited-angle cbct reconstruction via geometry-integrated cycle-domain denoising diffusion probabilistic models preprint diffusion & generative priors geometry calibration & motion compensation limited-angle tomography arxiv.org 2506.13545" }, { "id": "limited-angle-spect-image-reconstruction-using-deep-image-pr", "title": "Limited-angle SPECT image reconstruction using deep image prior", "year": 2025, "venue": "PMB", "preprint": false, "topics": [ "limited-angle", "self-supervised" ], "links": { "paper": "https://arxiv.org/abs/2503.18342" }, "_q": "limited-angle spect image reconstruction using deep image prior pmb limited-angle tomography self-supervised & untrained methods arxiv.org 2503.18342" }, { "id": "mindi-3d-iterative-deep-learning-in-3d-for-sparse-view-cone-", "title": "MInDI-3D: Iterative Deep Learning in 3D for Sparse-view Cone Beam Computed Tomography", "year": 2025, "venue": null, "preprint": true, "topics": [ "sparse-view", "cbct", "unrolling" ], "links": { "paper": "https://arxiv.org/abs/2508.09616" }, "_q": "mindi-3d: iterative deep learning in 3d for sparse-view cone beam computed tomography preprint sparse-view ct cone-beam ct deep unrolling & model-based learning arxiv.org 2508.09616" }, { "id": "photon-pile-up-normalizing-flow", "title": "Modeling X-Ray Photon Pile-Up with a Normalizing Flow", "year": 2025, "venue": "NeurIPS Workshop", "preprint": false, "topics": [ "spectral", "other" ], "links": { "paper": "https://arxiv.org/abs/2511.11863" }, "_q": "modeling x-ray photon pile-up with a normalizing flow neurips workshop spectral & dual-energy ct other topics arxiv.org 2511.11863" }, { "id": "monstr-model-oriented-neutron-strain-tomographic-reconstruct", "title": "MONSTR: Model-Oriented Neutron Strain Tomographic Reconstruction", "year": 2025, "venue": null, "preprint": true, "topics": [ "classical", "other" ], "links": { "paper": "https://arxiv.org/abs/2505.22187" }, "_q": "monstr: model-oriented neutron strain tomographic reconstruction preprint classical & iterative reconstruction other topics arxiv.org 2505.22187" }, { "id": "motion-grad", "title": "A Gradient-Based Approach to Fast and Accurate Head Motion Compensation in Cone-Beam CT", "year": 2025, "venue": "TMI", "preprint": false, "topics": [ "geometry", "cbct", "dynamic" ], "links": { "paper": "https://doi.org/10.1109/tmi.2024.3474250", "code": "https://github.com/mareikethies/geometry_gradients_CT" }, "abbr": "Motion-Grad", "_q": "a gradient-based approach to fast and accurate head motion compensation in cone-beam ct motion-grad tmi geometry calibration & motion compensation cone-beam ct dynamic & 4d ct doi.org tmi.2024.3474250 github.com geometry_gradients_ct" }, { "id": "neural-discrete-representation-learning-for-sparse-view-cbct", "title": "Neural Discrete Representation Learning for Sparse-View CBCT Reconstruction: From Algorithm Design to Prospective Multicenter Clinical Evaluation", "year": 2025, "venue": null, "preprint": true, "topics": [ "sparse-view", "cbct" ], "links": { "paper": "https://arxiv.org/abs/2512.00873" }, "_q": "neural discrete representation learning for sparse-view cbct reconstruction: from algorithm design to prospective multicenter clinical evaluation preprint sparse-view ct cone-beam ct arxiv.org 2512.00873" }, { "id": "noise-inspired-diffusion-model-for-generalizable-low-dose-ct", "title": "Noise-Inspired Diffusion Model for Generalizable Low-Dose CT Reconstruction", "year": 2025, "venue": "Med Image Anal", "preprint": false, "topics": [ "diffusion", "low-dose" ], "links": { "paper": "https://arxiv.org/abs/2506.22012", "code": "https://github.com/qgao21/NEED" }, "_q": "noise-inspired diffusion model for generalizable low-dose ct reconstruction med image anal diffusion & generative priors low-dose ct denoising arxiv.org 2506.22012 github.com need" }, { "id": "nonperiodic-dynamic-ct-reconstruction-using-backward-warping", "title": "Nonperiodic dynamic CT reconstruction using backward-warping INR with regularization of diffeomorphism (BIRD)", "year": 2025, "venue": null, "preprint": true, "topics": [ "inr", "dynamic" ], "links": { "paper": "https://arxiv.org/abs/2505.03463" }, "_q": "nonperiodic dynamic ct reconstruction using backward-warping inr with regularization of diffeomorphism (bird) preprint implicit neural representations dynamic & 4d ct arxiv.org 2505.03463" }, { "id": "ordered-subsets-multi-diffusion-model-for-sparse-view-ct-rec", "title": "Ordered-subsets Multi-diffusion Model for Sparse-view CT Reconstruction", "year": 2025, "venue": null, "preprint": true, "topics": [ "diffusion", "sparse-view" ], "links": { "paper": "https://arxiv.org/abs/2505.09985" }, "_q": "ordered-subsets multi-diffusion model for sparse-view ct reconstruction preprint diffusion & generative priors sparse-view ct arxiv.org 2505.09985" }, { "id": "physics-inspired-gaussian-kolmogorov-arnold-networks-for-x-r", "title": "Physics-Inspired Gaussian Kolmogorov-Arnold Networks for X-ray Scatter Correction in Cone-Beam CT", "year": 2025, "venue": null, "preprint": true, "topics": [ "scatter", "cbct" ], "links": { "paper": "https://arxiv.org/abs/2510.24579" }, "_q": "physics-inspired gaussian kolmogorov-arnold networks for x-ray scatter correction in cone-beam ct preprint scatter correction cone-beam ct arxiv.org 2510.24579" }, { "id": "prior-adapted-progressive-time-resolved-cbct-reconstruction-", "title": "Prior-Adapted Progressive Time-Resolved CBCT Reconstruction Using a Dynamic Reconstruction and Motion Estimation Method", "year": 2025, "venue": null, "preprint": true, "topics": [ "dynamic", "geometry", "cbct" ], "links": { "paper": "https://arxiv.org/abs/2504.18700" }, "_q": "prior-adapted progressive time-resolved cbct reconstruction using a dynamic reconstruction and motion estimation method preprint dynamic & 4d ct geometry calibration & motion compensation cone-beam ct arxiv.org 2504.18700" }, { "id": "projection-embedded-diffusion-bridge-for-ct-reconstruction-f", "title": "Projection Embedded Diffusion Bridge for CT Reconstruction from Incomplete Data", "year": 2025, "venue": null, "preprint": true, "topics": [ "diffusion", "limited-angle" ], "links": { "paper": "https://arxiv.org/abs/2510.22605" }, "_q": "projection embedded diffusion bridge for ct reconstruction from incomplete data preprint diffusion & generative priors limited-angle tomography arxiv.org 2510.22605" }, { "id": "diffraction-neural-volumetric-prior", "title": "Recover Biological Structure from Sparse-View Diffraction Images with Neural Volumetric Prior", "year": 2025, "venue": "ICCV", "preprint": false, "topics": [ "inr", "sparse-view", "other" ], "links": { "paper": "https://arxiv.org/abs/2510.16391" }, "_q": "recover biological structure from sparse-view diffraction images with neural volumetric prior iccv implicit neural representations sparse-view ct other topics arxiv.org 2510.16391" }, { "id": "remar-ds-recalibrated-feature-learning-for-metal-artifact-re", "title": "ReMAR-DS: Recalibrated Feature Learning for Metal Artifact Reduction and CT Domain Transformation", "year": 2025, "venue": "ICIAP", "preprint": false, "topics": [ "metal-artifact" ], "links": { "paper": "https://arxiv.org/abs/2506.19531" }, "_q": "remar-ds: recalibrated feature learning for metal artifact reduction and ct domain transformation iciap metal artifact reduction arxiv.org 2506.19531" }, { "id": "resolution-agnostic-neural-operators-for-multi-rate-sparse-v", "title": "Resolution-Agnostic Neural Operators for Multi-Rate Sparse-View CT", "year": 2025, "venue": null, "preprint": true, "topics": [ "sparse-view", "unrolling" ], "links": { "paper": "https://arxiv.org/abs/2512.12236", "code": "https://github.com/neuraloperator/sparse_ct" }, "_q": "resolution-agnostic neural operators for multi-rate sparse-view ct preprint sparse-view ct deep unrolling & model-based learning arxiv.org 2512.12236 github.com sparse_ct" }, { "id": "sdb", "title": "System-Embedded Diffusion Bridge Models", "year": 2025, "venue": "NeurIPS", "preprint": false, "topics": [ "diffusion", "classical" ], "links": { "paper": "https://arxiv.org/abs/2506.23726", "code": "https://github.com/sobieskibj/sdb" }, "abbr": "SDB", "_q": "system-embedded diffusion bridge models sdb neurips diffusion & generative priors classical & iterative reconstruction arxiv.org 2506.23726 github.com sdb" }, { "id": "semantic-contrastive-learning-for-orthogonal-x-ray-computed-", "title": "Semantic contrastive learning for orthogonal X-ray computed tomography reconstruction", "year": 2025, "venue": "Fully3D", "preprint": false, "topics": [ "sparse-view", "unrolling" ], "links": { "paper": "https://arxiv.org/abs/2512.22674" }, "_q": "semantic contrastive learning for orthogonal x-ray computed tomography reconstruction fully3d sparse-view ct deep unrolling & model-based learning arxiv.org 2512.22674" }, { "id": "spener", "title": "Unsupervised Self-Prior Embedding Neural Representation for Sparse-View CT Reconstruction", "year": 2025, "venue": "AAAI", "preprint": false, "topics": [ "inr", "sparse-view", "self-supervised" ], "links": { "paper": "https://doi.org/10.1609/aaai.v39i7.32794", "code": "https://github.com/MeijiTian/Spener" }, "abbr": "Spener", "_q": "unsupervised self-prior embedding neural representation for sparse-view ct reconstruction spener aaai implicit neural representations sparse-view ct self-supervised & untrained methods doi.org aaai.v39i7.32794 github.com spener" }, { "id": "synthetic-ct-image-generation-from-cbct-a-systematic-review", "title": "Synthetic CT image generation from CBCT: A Systematic Review", "year": 2025, "venue": "TRPMS", "preprint": false, "topics": [ "cbct", "survey" ], "links": { "paper": "https://arxiv.org/abs/2501.13972" }, "_q": "synthetic ct image generation from cbct: a systematic review trpms cone-beam ct surveys & reviews arxiv.org 2501.13972" }, { "id": "time-resolved-dynamic-cbct-reconstruction-using-prior-model-", "title": "Time-resolved dynamic CBCT reconstruction using prior-model-free spatiotemporal Gaussian representation (PMF-STGR)", "year": 2025, "venue": null, "preprint": true, "topics": [ "gaussian", "dynamic", "cbct" ], "links": { "paper": "https://arxiv.org/abs/2503.22139" }, "_q": "time-resolved dynamic cbct reconstruction using prior-model-free spatiotemporal gaussian representation (pmf-stgr) preprint gaussian splatting dynamic & 4d ct cone-beam ct arxiv.org 2503.22139" }, { "id": "ultrafast-deep-learning-based-scatter-estimation-in-cone-bea", "title": "Ultrafast Deep Learning-Based Scatter Estimation in Cone-Beam Computed Tomography", "year": 2025, "venue": null, "preprint": true, "topics": [ "scatter", "cbct" ], "links": { "paper": "https://arxiv.org/abs/2509.08973" }, "_q": "ultrafast deep learning-based scatter estimation in cone-beam computed tomography preprint scatter correction cone-beam ct arxiv.org 2509.08973" }, { "id": "vol3dgs", "title": "Volumetrically Consistent 3D Gaussian Rasterization", "year": 2025, "venue": "CVPR", "preprint": false, "topics": [ "gaussian" ], "links": { "paper": "https://arxiv.org/abs/2412.03378", "code": "https://github.com/chinmay0301ucsd/Vol3DGS" }, "abbr": "Vol3DGS", "_q": "volumetrically consistent 3d gaussian rasterization vol3dgs cvpr gaussian splatting arxiv.org 2412.03378 github.com vol3dgs" }, { "id": "when-are-diffusion-priors-helpful-in-sparse-reconstruction-a", "title": "When are Diffusion Priors Helpful in Sparse Reconstruction? A Study with Sparse-view CT", "year": 2025, "venue": "ISBI", "preprint": false, "topics": [ "diffusion", "sparse-view" ], "links": { "paper": "https://arxiv.org/abs/2502.02771" }, "_q": "when are diffusion priors helpful in sparse reconstruction? a study with sparse-view ct isbi diffusion & generative priors sparse-view ct arxiv.org 2502.02771" }, { "id": "x-grm-large-gaussian-reconstruction-model-for-sparse-view-x-", "title": "X-GRM: Large Gaussian Reconstruction Model for Sparse-view X-rays to Computed Tomography", "year": 2025, "venue": null, "preprint": true, "topics": [ "gaussian", "sparse-view" ], "links": { "paper": "https://arxiv.org/abs/2505.15235", "code": "https://github.com/CUHK-AIM-Group/X-GRM" }, "_q": "x-grm: large gaussian reconstruction model for sparse-view x-rays to computed tomography preprint gaussian splatting sparse-view ct arxiv.org 2505.15235 github.com x-grm" }, { "id": "x2-gaussian", "title": "X2-Gaussian: 4D Radiative Gaussian Splatting for Continuous-Time Tomographic Reconstruction", "year": 2025, "venue": "ICCV", "preprint": false, "topics": [ "gaussian", "dynamic" ], "links": { "paper": "https://doi.org/10.1109/iccv51701.2025.02293", "code": "https://github.com/yuyouxixi/x2-gaussian" }, "abbr": "X2-Gaussian", "_q": "x2-gaussian: 4d radiative gaussian splatting for continuous-time tomographic reconstruction x2-gaussian iccv gaussian splatting dynamic & 4d ct doi.org iccv51701.2025.02293 github.com x2-gaussian" }, { "id": "zero-shot-ct-super-resolution-using-diffusion-based-2d-proje", "title": "Zero-shot CT Super-Resolution using Diffusion-based 2D Projection Priors and Signed 3D Gaussians", "year": 2025, "venue": null, "preprint": true, "topics": [ "gaussian", "diffusion", "self-supervised" ], "links": { "paper": "https://arxiv.org/abs/2508.15151" }, "_q": "zero-shot ct super-resolution using diffusion-based 2d projection priors and signed 3d gaussians preprint gaussian splatting diffusion & generative priors self-supervised & untrained methods arxiv.org 2508.15151" }, { "id": "zero-shot-low-dose-ct-denoising-via-sinogram-flicking", "title": "Zero-Shot Low-dose CT Denoising via Sinogram Flicking", "year": 2025, "venue": null, "preprint": true, "topics": [ "low-dose", "self-supervised" ], "links": { "paper": "https://arxiv.org/abs/2504.07927" }, "_q": "zero-shot low-dose ct denoising via sinogram flicking preprint low-dose ct denoising self-supervised & untrained methods arxiv.org 2504.07927" }, { "id": "baggagect", "title": "Fan-Beam CT Reconstruction for Unaligned Sparse-View X-Ray Baggage Data", "year": 2024, "venue": null, "preprint": true, "topics": [ "sparse-view", "geometry" ], "links": { "paper": "https://arxiv.org/abs/2412.03036" }, "abbr": "BaggageCT", "_q": "fan-beam ct reconstruction for unaligned sparse-view x-ray baggage data baggagect preprint sparse-view ct geometry calibration & motion compensation arxiv.org 2412.03036" }, { "id": "data-driven-filter-design-in-fbp-transforming-ct-reconstru", "title": "Data-Driven Filter Design in FBP: Transforming CT Reconstruction with Trainable Fourier Series", "year": 2024, "venue": null, "preprint": true, "topics": [ "classical" ], "links": { "paper": "https://arxiv.org/abs/2401.16039" }, "_q": "data-driven filter design in fbp: transforming ct reconstruction with trainable fourier series preprint classical & iterative reconstruction arxiv.org 2401.16039" }, { "id": "dif-gaussian", "title": "Learning 3D Gaussians for Extremely Sparse-View Cone-Beam CT Reconstruction", "year": 2024, "venue": "MICCAI", "preprint": false, "topics": [ "gaussian", "sparse-view", "cbct" ], "links": { "paper": "https://doi.org/10.1007/978-3-031-72104-5_41", "code": "https://github.com/xmed-lab/DIF-Gaussian" }, "abbr": "DIF-Gaussian", "_q": "learning 3d gaussians for extremely sparse-view cone-beam ct reconstruction dif-gaussian miccai gaussian splatting sparse-view ct cone-beam ct doi.org 978-3-031-72104-5_41 github.com dif-gaussian" }, { "id": "diffrecon", "title": "Diffusion Models for Medical Image Reconstruction", "year": 2024, "venue": "BJR|AI", "preprint": false, "topics": [ "survey", "diffusion" ], "links": { "paper": "https://doi.org/10.1093/bjrai/ubae013" }, "abbr": "DiffRecon", "_q": "diffusion models for medical image reconstruction diffrecon bjr|ai surveys & reviews diffusion & generative priors doi.org ubae013" }, { "id": "dudodp-mar", "title": "Unsupervised CT Metal Artifact Reduction by Plugging Diffusion Priors in Dual Domains", "year": 2024, "venue": "TMI", "preprint": false, "topics": [ "metal-artifact", "diffusion", "self-supervised" ], "links": { "paper": "https://doi.org/10.1109/tmi.2024.3351201", "code": "https://github.com/DeepXuan/DuDoDp-MAR" }, "abbr": "DuDoDp-MAR", "_q": "unsupervised ct metal artifact reduction by plugging diffusion priors in dual domains dudodp-mar tmi metal artifact reduction diffusion & generative priors self-supervised & untrained methods doi.org tmi.2024.3351201 github.com dudodp-mar" }, { "id": "eagle-an-edge-aware-gradient-localization-enhanced-loss-fo", "title": "EAGLE: An Edge-Aware Gradient Localization Enhanced Loss for CT Image Reconstruction", "year": 2024, "venue": null, "preprint": true, "topics": [ "unrolling", "low-dose" ], "links": { "paper": "https://arxiv.org/abs/2403.10695", "code": "https://github.com/sypsyp97/Eagle_Loss" }, "_q": "eagle: an edge-aware gradient localization enhanced loss for ct image reconstruction preprint deep unrolling & model-based learning low-dose ct denoising arxiv.org 2403.10695 github.com eagle_loss" }, { "id": "generative-modeling-in-sinogram-domain-for-sparse-view-ct-", "title": "Generative Modeling in Sinogram Domain for Sparse-view CT Reconstruction", "year": 2024, "venue": "TRPMS", "preprint": false, "topics": [ "diffusion", "sparse-view" ], "links": { "paper": "https://arxiv.org/abs/2211.13926" }, "_q": "generative modeling in sinogram domain for sparse-view ct reconstruction trpms diffusion & generative priors sparse-view ct arxiv.org 2211.13926" }, { "id": "incode", "title": "INCODE: Implicit Neural Conditioning with Prior Knowledge Embeddings", "year": 2024, "venue": "WACV", "preprint": false, "topics": [ "inr" ], "links": { "paper": "https://doi.org/10.1109/wacv57701.2024.00133", "code": "https://github.com/xmindflow/INCODE" }, "abbr": "INCODE", "_q": "incode: implicit neural conditioning with prior knowledge embeddings incode wacv implicit neural representations doi.org wacv57701.2024.00133 github.com incode" }, { "id": "inr-joint", "title": "Implicit Neural Representations for Robust Joint Sparse-View CT Reconstruction", "year": 2024, "venue": "TMLR", "preprint": false, "topics": [ "inr", "sparse-view" ], "links": { "paper": "https://arxiv.org/abs/2405.02509", "code": "https://github.com/jiayangshi/INR4JointCTRecon" }, "abbr": "INR-Joint", "_q": "implicit neural representations for robust joint sparse-view ct reconstruction inr-joint tmlr implicit neural representations sparse-view ct arxiv.org 2405.02509 github.com inr4jointctrecon" }, { "id": "r2-gaussian", "title": "R2-Gaussian: Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction", "year": 2024, "venue": "NeurIPS", "preprint": false, "topics": [ "gaussian", "sparse-view" ], "links": { "paper": "https://arxiv.org/abs/2405.20693", "code": "https://github.com/Ruyi-Zha/r2_gaussian" }, "abbr": "R2-Gaussian", "_q": "r2-gaussian: rectifying radiative gaussian splatting for tomographic reconstruction r2-gaussian neurips gaussian splatting sparse-view ct arxiv.org 2405.20693 github.com r2_gaussian" }, { "id": "sax-nerf", "title": "Structure-Aware Sparse-View X-Ray 3D Reconstruction", "year": 2024, "venue": "CVPR", "preprint": false, "topics": [ "inr", "sparse-view" ], "links": { "paper": "https://doi.org/10.1109/cvpr52733.2024.01062", "code": "https://github.com/caiyuanhao1998/SAX-NeRF" }, "abbr": "SAX-NeRF", "_q": "structure-aware sparse-view x-ray 3d reconstruction sax-nerf cvpr implicit neural representations sparse-view ct doi.org cvpr52733.2024.01062 github.com sax-nerf" }, { "id": "scatter-dl", "title": "Scatter Correction Using Deep Learning for Cone-Beam Computed Tomography", "year": 2024, "venue": "DL4X-ray", "preprint": false, "topics": [ "scatter", "cbct" ], "links": { "paper": "https://doi.org/10.1007/978-3-031-75653-5_6" }, "abbr": "Scatter-DL", "_q": "scatter correction using deep learning for cone-beam computed tomography scatter-dl dl4x-ray scatter correction cone-beam ct doi.org 978-3-031-75653-5_6" }, { "id": "soul-net", "title": "SOUL-Net: A Sparse and Low-Rank Unrolling Network for Spectral CT Image Reconstruction", "year": 2024, "venue": "TNNLS", "preprint": false, "topics": [ "spectral", "unrolling" ], "links": { "paper": "https://doi.org/10.1109/tnnls.2023.3319408", "code": "https://github.com/scuchenxiang/SOUL-Net" }, "abbr": "SOUL-Net", "_q": "soul-net: a sparse and low-rank unrolling network for spectral ct image reconstruction soul-net tnnls spectral & dual-energy ct deep unrolling & model-based learning doi.org tnnls.2023.3319408 github.com soul-net" }, { "id": "sword", "title": "Stage-by-Stage Wavelet Optimization Refinement Diffusion Model for Sparse-View CT Reconstruction", "year": 2024, "venue": "TMI", "preprint": false, "topics": [ "sparse-view", "diffusion" ], "links": { "paper": "https://doi.org/10.1109/tmi.2024.3355455", "code": "https://github.com/yqx7150/SWORD" }, "abbr": "SWORD", "_q": "stage-by-stage wavelet optimization refinement diffusion model for sparse-view ct reconstruction sword tmi sparse-view ct diffusion & generative priors doi.org tmi.2024.3355455 github.com sword" }, { "id": "x-gaussian", "title": "Radiative Gaussian Splatting for Efficient X-Ray Novel View Synthesis", "year": 2024, "venue": "ECCV", "preprint": false, "topics": [ "gaussian" ], "links": { "paper": "https://arxiv.org/abs/2403.04116", "code": "https://github.com/caiyuanhao1998/X-Gaussian" }, "abbr": "X-Gaussian", "_q": "radiative gaussian splatting for efficient x-ray novel view synthesis x-gaussian eccv gaussian splatting arxiv.org 2403.04116 github.com x-gaussian" }, { "id": "3dip", "title": "Solving 3D Inverse Problems Using Pre-Trained 2D Diffusion Models", "year": 2023, "venue": "CVPR", "preprint": false, "topics": [ "diffusion" ], "links": { "paper": "https://doi.org/10.1109/cvpr52729.2023.02159" }, "abbr": "3DIP", "_q": "solving 3d inverse problems using pre-trained 2d diffusion models 3dip cvpr diffusion & generative priors doi.org cvpr52729.2023.02159" }, { "id": "ascon", "title": "ASCON: Anatomy-Aware Supervised Contrastive Learning Framework for Low-Dose CT Denoising", "year": 2023, "venue": "MICCAI", "preprint": false, "topics": [ "low-dose" ], "links": { "paper": "https://doi.org/10.1007/978-3-031-43999-5_34", "code": "https://github.com/hao1635/ASCON" }, "abbr": "ASCON", "_q": "ascon: anatomy-aware supervised contrastive learning framework for low-dose ct denoising ascon miccai low-dose ct denoising doi.org 978-3-031-43999-5_34 github.com ascon" }, { "id": "ctformer", "title": "CTformer: Convolution-Free Token2Token Dilated Vision Transformer for Low-Dose CT Denoising", "year": 2023, "venue": "PMB", "preprint": false, "topics": [ "low-dose" ], "links": { "paper": "https://doi.org/10.1088/1361-6560/acc000", "code": "https://github.com/wdayang/CTformer" }, "abbr": "CTformer", "_q": "ctformer: convolution-free token2token dilated vision transformer for low-dose ct denoising ctformer pmb low-dose ct denoising doi.org acc000 github.com ctformer" }, { "id": "dadn", "title": "Domain-adaptive denoising network for low-dose CT via noise estimation and transfer learning", "year": 2023, "venue": "Med Phys", "preprint": false, "topics": [ "low-dose" ], "links": { "paper": "https://doi.org/10.1002/mp.15952" }, "abbr": "DADN", "_q": "domain-adaptive denoising network for low-dose ct via noise estimation and transfer learning dadn med phys low-dose ct denoising doi.org mp.15952" }, { "id": "dddm", "title": "Dual-Domain Diffusion Model for Sparse-View CT Reconstruction", "year": 2023, "venue": null, "preprint": true, "topics": [ "sparse-view", "diffusion" ], "links": { "paper": "https://doi.org/10.36227/techrxiv.23726703", "code": "https://github.com/YC-Markus/code-for-DDDM" }, "abbr": "DDDM", "_q": "dual-domain diffusion model for sparse-view ct reconstruction dddm preprint sparse-view ct diffusion & generative priors doi.org techrxiv.23726703 github.com code-for-dddm" }, { "id": "freeseed", "title": "FreeSeed: Frequency-Band-Aware and Self-Guided Network for Sparse-View CT Reconstruction", "year": 2023, "venue": "MICCAI", "preprint": false, "topics": [ "sparse-view", "unrolling" ], "links": { "paper": "https://doi.org/10.1007/978-3-031-43999-5_24", "code": "https://github.com/Masaaki-75/freeseed" }, "abbr": "FreeSeed", "_q": "freeseed: frequency-band-aware and self-guided network for sparse-view ct reconstruction freeseed miccai sparse-view ct deep unrolling & model-based learning doi.org 978-3-031-43999-5_24 github.com freeseed" }, { "id": "gglf", "title": "Gradient-based geometry learning for fan-beam CT reconstruction", "year": 2023, "venue": "PMB", "preprint": false, "topics": [ "geometry" ], "links": { "paper": "https://doi.org/10.1088/1361-6560/acf90e" }, "abbr": "GGLF", "_q": "gradient-based geometry learning for fan-beam ct reconstruction gglf pmb geometry calibration & motion compensation doi.org acf90e" }, { "id": "irds", "title": "Iterative reconstruction of low-dose CT based on differential sparse", "year": 2023, "venue": "BSPC", "preprint": false, "topics": [ "low-dose", "classical" ], "links": { "paper": "https://doi.org/10.1016/j.bspc.2022.104204" }, "abbr": "IRDS", "_q": "iterative reconstruction of low-dose ct based on differential sparse irds bspc low-dose ct denoising classical & iterative reconstruction doi.org j.bspc.2022.104204" }, { "id": "piner", "title": "PINER: Prior-Informed Implicit Neural Representation Learning for Test-Time Adaptation in Sparse-View CT Reconstruction", "year": 2023, "venue": "WACV", "preprint": false, "topics": [ "inr", "sparse-view", "self-supervised" ], "links": { "paper": "https://doi.org/10.1109/wacv56688.2023.00197", "code": "https://github.com/efzero/PINER" }, "abbr": "PINER", "_q": "piner: prior-informed implicit neural representation learning for test-time adaptation in sparse-view ct reconstruction piner wacv implicit neural representations sparse-view ct self-supervised & untrained methods doi.org wacv56688.2023.00197 github.com piner" }, { "id": "polyner", "title": "Unsupervised Polychromatic Neural Representation for CT Metal Artifact Reduction", "year": 2023, "venue": "NeurIPS", "preprint": false, "topics": [ "metal-artifact", "inr", "self-supervised" ], "links": { "paper": "https://arxiv.org/abs/2306.15203", "code": "https://github.com/iwuqing/Polyner" }, "abbr": "Polyner", "_q": "unsupervised polychromatic neural representation for ct metal artifact reduction polyner neurips metal artifact reduction implicit neural representations self-supervised & untrained methods arxiv.org 2306.15203 github.com polyner" }, { "id": "semimar", "title": "SemiMAR: Semi-Supervised Learning for CT Metal Artifact Reduction", "year": 2023, "venue": "JBHI", "preprint": false, "topics": [ "metal-artifact", "self-supervised" ], "links": { "paper": "https://doi.org/10.1109/jbhi.2023.3312292", "code": "https://github.com/zjk1988/SemiMAR" }, "abbr": "SemiMAR", "_q": "semimar: semi-supervised learning for ct metal artifact reduction semimar jbhi metal artifact reduction self-supervised & untrained methods doi.org jbhi.2023.3312292 github.com semimar" }, { "id": "spqi", "title": "Structure-preserving quality improvement of cone beam CT images using contrastive learning", "year": 2023, "venue": "CBM", "preprint": false, "topics": [ "cbct" ], "links": { "paper": "https://doi.org/10.1016/j.compbiomed.2023.106803" }, "abbr": "SPQI", "_q": "structure-preserving quality improvement of cone beam ct images using contrastive learning spqi cbm cone-beam ct doi.org j.compbiomed.2023.106803" }, { "id": "synergizing-physics-model-based-and-data-driven-methods-fo", "title": "Synergizing Physics/Model-based and Data-driven Methods for Low-Dose CT", "year": 2023, "venue": "IEEE SPM", "preprint": false, "topics": [ "low-dose" ], "links": { "paper": "https://arxiv.org/abs/2203.15725" }, "_q": "synergizing physics/model-based and data-driven methods for low-dose ct ieee spm low-dose ct denoising arxiv.org 2203.15725" }, { "id": "acdnet", "title": "Adaptive Convolutional Dictionary Network for CT Metal Artifact Reduction", "year": 2022, "venue": "IJCAI", "preprint": false, "topics": [ "metal-artifact", "unrolling" ], "links": { "paper": "https://doi.org/10.24963/ijcai.2022/195", "code": "https://github.com/hongwang01/ACDNet" }, "abbr": "ACDNet", "_q": "adaptive convolutional dictionary network for ct metal artifact reduction acdnet ijcai metal artifact reduction deep unrolling & model-based learning doi.org 195 github.com acdnet" }, { "id": "acid-a", "title": "Stabilizing deep tomographic reconstruction - Part A. Hybrid framework and experimental results", "year": 2022, "venue": "Patterns", "preprint": false, "topics": [ "unrolling", "self-supervised" ], "links": { "paper": "https://doi.org/10.1016/j.patter.2022.100474" }, "abbr": "ACID-A", "_q": "stabilizing deep tomographic reconstruction - part a. hybrid framework and experimental results acid-a patterns deep unrolling & model-based learning self-supervised & untrained methods doi.org j.patter.2022.100474" }, { "id": "acid-b", "title": "Stabilizing deep tomographic reconstruction - Part B. Convergence analysis and adversarial attacks", "year": 2022, "venue": "Patterns", "preprint": false, "topics": [ "unrolling", "self-supervised" ], "links": { "paper": "https://doi.org/10.1016/j.patter.2022.100475" }, "abbr": "ACID-B", "_q": "stabilizing deep tomographic reconstruction - part b. convergence analysis and adversarial attacks acid-b patterns deep unrolling & model-based learning self-supervised & untrained methods doi.org j.patter.2022.100475" }, { "id": "ccn-cl", "title": "CCN-CL: A content-noise complementary network with contrastive learning for low-dose computed tomography denoising", "year": 2022, "venue": "CBM", "preprint": false, "topics": [ "low-dose" ], "links": { "paper": "https://doi.org/10.1016/j.compbiomed.2022.105759" }, "abbr": "CCN-CL", "_q": "ccn-cl: a content-noise complementary network with contrastive learning for low-dose computed tomography denoising ccn-cl cbm low-dose ct denoising doi.org j.compbiomed.2022.105759" }, { "id": "cocodiff-a-contextual-conditional-diffusion-model-for-low-", "title": "CoCoDiff: A Contextual Conditional Diffusion Model for Low-dose CT Image Denoising", "year": 2022, "venue": "SPIE DXRT", "preprint": false, "topics": [ "diffusion", "low-dose" ], "links": { "paper": "https://doi.org/10.1117/12.2634939" }, "_q": "cocodiff: a contextual conditional diffusion model for low-dose ct image denoising spie dxrt diffusion & generative priors low-dose ct denoising doi.org 12.2634939" }, { "id": "ddcl", "title": "Dual domain closed-loop learning for sparse-view CT reconstruction", "year": 2022, "venue": "ICIFXCT", "preprint": false, "topics": [ "sparse-view", "unrolling" ], "links": { "paper": "https://doi.org/10.1117/12.2646639" }, "abbr": "DDCL", "_q": "dual domain closed-loop learning for sparse-view ct reconstruction ddcl icifxct sparse-view ct deep unrolling & model-based learning doi.org 12.2646639" }, { "id": "desdgan", "title": "A Dual-Encoder-Single-Decoder Based Low-Dose CT Denoising Network", "year": 2022, "venue": "JBHI", "preprint": false, "topics": [ "low-dose" ], "links": { "paper": "https://doi.org/10.1109/jbhi.2022.3155788", "code": "https://github.com/hanzefang/DESDGAN" }, "abbr": "DESDGAN", "_q": "a dual-encoder-single-decoder based low-dose ct denoising network desdgan jbhi low-dose ct denoising doi.org jbhi.2022.3155788 github.com desdgan" }, { "id": "dfdlm", "title": "A Dataset-free Deep Learning Method for Low-Dose CT Image Reconstruction", "year": 2022, "venue": "Inverse Problems", "preprint": false, "topics": [ "low-dose", "self-supervised" ], "links": { "paper": "https://arxiv.org/abs/2205.00463" }, "abbr": "DFDLM", "_q": "a dataset-free deep learning method for low-dose ct image reconstruction dfdlm inverse problems low-dose ct denoising self-supervised & untrained methods arxiv.org 2205.00463" }, { "id": "dgr-2", "title": "An Unsupervised Reconstruction Method For Low-Dose CT Using Deep Generative Regularization Prior", "year": 2022, "venue": "BSPC", "preprint": false, "topics": [ "low-dose", "self-supervised" ], "links": { "paper": "https://arxiv.org/abs/2012.06448", "code": "https://github.com/mozanunal/SparseCT" }, "abbr": "DGR-2", "_q": "an unsupervised reconstruction method for low-dose ct using deep generative regularization prior dgr-2 bspc low-dose ct denoising self-supervised & untrained methods arxiv.org 2012.06448 github.com sparsect" }, { "id": "diffmed", "title": "Diffusion Models for Medical Image Analysis: A Comprehensive Survey", "year": 2022, "venue": null, "preprint": true, "topics": [ "survey", "diffusion" ], "links": { "paper": "https://arxiv.org/abs/2211.07804" }, "abbr": "DiffMed", "_q": "diffusion models for medical image analysis: a comprehensive survey diffmed preprint surveys & reviews diffusion & generative priors arxiv.org 2211.07804" }, { "id": "dream-net", "title": "DREAM-Net: Deep Residual Error Iterative Minimization Network for Sparse-View CT Reconstruction", "year": 2022, "venue": "TMI", "preprint": false, "topics": [ "sparse-view", "unrolling" ], "links": { "paper": "https://doi.org/10.1109/jbhi.2022.3225697" }, "abbr": "DREAM-Net", "_q": "dream-net: deep residual error iterative minimization network for sparse-view ct reconstruction dream-net tmi sparse-view ct deep unrolling & model-based learning doi.org jbhi.2022.3225697" }, { "id": "du-gan", "title": "DU-GAN: Generative Adversarial Networks with Dual-Domain U-Net Based Discriminators for Low-Dose CT Denoising", "year": 2022, "venue": "TIM", "preprint": false, "topics": [ "low-dose" ], "links": { "paper": "https://doi.org/10.1109/tim.2021.3128703", "code": "https://github.com/Hzzone/DU-GAN" }, "abbr": "DU-GAN", "_q": "du-gan: generative adversarial networks with dual-domain u-net based discriminators for low-dose ct denoising du-gan tim low-dose ct denoising doi.org tim.2021.3128703 github.com du-gan" }, { "id": "dudotrans", "title": "DuDoTrans: Dual-Domain Transformer for Sparse-View CT Reconstruction", "year": 2022, "venue": "MLMIR", "preprint": false, "topics": [ "sparse-view", "unrolling" ], "links": { "paper": "https://doi.org/10.1007/978-3-031-17247-2_9", "code": "https://github.com/cewang-sysu/DuDoTrans" }, "abbr": "DuDoTrans", "_q": "dudotrans: dual-domain transformer for sparse-view ct reconstruction dudotrans mlmir sparse-view ct deep unrolling & model-based learning doi.org 978-3-031-17247-2_9 github.com dudotrans" }, { "id": "easel", "title": "Iterative Reconstruction for Low-Dose CT using Deep Gradient Priors of Generative Model", "year": 2022, "venue": "TRPMS", "preprint": false, "topics": [ "diffusion", "low-dose", "classical" ], "links": { "paper": "https://doi.org/10.1109/trpms.2022.3148373", "code": "https://github.com/yqx7150/EASEL" }, "abbr": "EASEL", "_q": "iterative reconstruction for low-dose ct using deep gradient priors of generative model easel trpms diffusion & generative priors low-dose ct denoising classical & iterative reconstruction doi.org trpms.2022.3148373 github.com easel" }, { "id": "font-sir", "title": "FONT-SIR: Fourth-Order Nonlocal Tensor Decomposition Model for Spectral CT Image Reconstruction", "year": 2022, "venue": "TMI", "preprint": false, "topics": [ "spectral" ], "links": { "paper": "https://doi.org/10.1109/tmi.2022.3156270" }, "abbr": "FONT-SIR", "_q": "font-sir: fourth-order nonlocal tensor decomposition model for spectral ct image reconstruction font-sir tmi spectral & dual-energy ct doi.org tmi.2022.3156270" }, { "id": "gmm-unnet", "title": "Noise Characteristics Modeled Unsupervised Network for Robust CT Image Reconstruction", "year": 2022, "venue": "TMI", "preprint": false, "topics": [ "self-supervised" ], "links": { "paper": "https://doi.org/10.1109/tmi.2022.3197400" }, "abbr": "GMM-unNet", "_q": "noise characteristics modeled unsupervised network for robust ct image reconstruction gmm-unnet tmi self-supervised & untrained methods doi.org tmi.2022.3197400" }, { "id": "idol-net", "title": "IDOL-Net: An Interactive Dual-Domain Parallel Network for CT Metal Artifact Reduction", "year": 2022, "venue": "TRPMS", "preprint": false, "topics": [ "metal-artifact", "unrolling" ], "links": { "paper": "https://doi.org/10.1109/trpms.2022.3171440", "code": "https://github.com/zjk1988/IDOL-Net" }, "abbr": "IDOL-Net", "_q": "idol-net: an interactive dual-domain parallel network for ct metal artifact reduction idol-net trpms metal artifact reduction deep unrolling & model-based learning doi.org trpms.2022.3171440 github.com idol-net" }, { "id": "low-dose-ct-using-denoising-diffusion-probabilistic-model-", "title": "Low-Dose CT Using Denoising Diffusion Probabilistic Model for 20× Speedup", "year": 2022, "venue": null, "preprint": true, "topics": [ "diffusion", "low-dose" ], "links": { "paper": "https://arxiv.org/abs/2209.15136" }, "_q": "low-dose ct using denoising diffusion probabilistic model for 20× speedup preprint diffusion & generative priors low-dose ct denoising arxiv.org 2209.15136" }, { "id": "malar", "title": "Multiple Adversarial Learning based Angiography Reconstruction for Ultra-low-dose Contrast Medium CT", "year": 2022, "venue": "JBHI", "preprint": false, "topics": [ "low-dose" ], "links": { "paper": "https://doi.org/10.1109/jbhi.2022.3213595", "code": "https://github.com/HIC-SYSU/MALAR" }, "abbr": "MALAR", "_q": "multiple adversarial learning based angiography reconstruction for ultra-low-dose contrast medium ct malar jbhi low-dose ct denoising doi.org jbhi.2022.3213595 github.com malar" }, { "id": "naf", "title": "NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstruction", "year": 2022, "venue": "MICCAI", "preprint": false, "topics": [ "inr", "cbct", "sparse-view" ], "links": { "paper": "https://arxiv.org/abs/2209.14540", "code": "https://github.com/Ruyi-Zha/naf_cbct" }, "abbr": "NAF", "_q": "naf: neural attenuation fields for sparse-view cbct reconstruction naf miccai implicit neural representations cone-beam ct sparse-view ct arxiv.org 2209.14540 github.com naf_cbct" }, { "id": "planet", "title": "Learning Projection Views for Sparse-View CT Reconstruction", "year": 2022, "venue": "ACM MM", "preprint": false, "topics": [ "sparse-view" ], "links": { "paper": "https://doi.org/10.1145/3503161.3548204" }, "abbr": "PLANet", "_q": "learning projection views for sparse-view ct reconstruction planet acm mm sparse-view ct doi.org 3503161.3548204" }, { "id": "snaf", "title": "SNAF: Sparse-View CBCT Reconstruction with Neural Attenuation Fields", "year": 2022, "venue": null, "preprint": true, "topics": [ "inr", "cbct", "sparse-view" ], "links": { "paper": "https://arxiv.org/abs/2211.17048" }, "abbr": "SNAF", "_q": "snaf: sparse-view cbct reconstruction with neural attenuation fields snaf preprint implicit neural representations cone-beam ct sparse-view ct arxiv.org 2211.17048" }, { "id": "uncertainr-uncertainty-quantification-of-end-to-end-implic", "title": "UncertaINR: Uncertainty Quantification of End-to-End Implicit Neural Representations for Computed Tomography", "year": 2022, "venue": null, "preprint": true, "topics": [ "inr" ], "links": { "paper": "https://arxiv.org/abs/2202.10847" }, "_q": "uncertainr: uncertainty quantification of end-to-end implicit neural representations for computed tomography preprint implicit neural representations arxiv.org 2202.10847" }, { "id": "undip", "title": "Sparse-view and limited-angle CT reconstruction with untrained networks and deep image prior", "year": 2022, "venue": "CMPB", "preprint": false, "topics": [ "limited-angle", "sparse-view", "self-supervised" ], "links": { "paper": "https://doi.org/10.1016/j.cmpb.2022.107167" }, "abbr": "UNDIP", "_q": "sparse-view and limited-angle ct reconstruction with untrained networks and deep image prior undip cmpb limited-angle tomography sparse-view ct self-supervised & untrained methods doi.org j.cmpb.2022.107167" }, { "id": "alpd", "title": "Adversarially learned iterative reconstruction for imaging inverse problems", "year": 2021, "venue": "SSVM", "preprint": false, "topics": [ "classical" ], "links": { "paper": "https://arxiv.org/abs/2103.16151", "code": "https://github.com/Subhadip-1/adversarial_primal_dual_tomography" }, "abbr": "ALPD", "_q": "adversarially learned iterative reconstruction for imaging inverse problems alpd ssvm classical & iterative reconstruction arxiv.org 2103.16151 github.com adversarial_primal_dual_tomography" }, { "id": "casredscan", "title": "Limited View Tomographic Reconstruction Using a Cascaded Residual Dense Spatial-Channel Attention Network With Projection Data Fidelity Layer", "year": 2021, "venue": "TMI", "preprint": false, "topics": [ "limited-angle", "unrolling" ], "links": { "paper": "https://doi.org/10.1109/tmi.2021.3066318" }, "abbr": "CasRedSCAN", "_q": "limited view tomographic reconstruction using a cascaded residual dense spatial-channel attention network with projection data fidelity layer casredscan tmi limited-angle tomography deep unrolling & model-based learning doi.org tmi.2021.3066318" }, { "id": "clear", "title": "CLEAR: Comprehensive Learning Enabled Adversarial Reconstruction for Subtle Structure Enhanced Low-Dose CT Imaging", "year": 2021, "venue": "TMI", "preprint": false, "topics": [ "low-dose" ], "links": { "paper": "https://doi.org/10.1109/tmi.2021.3097808" }, "abbr": "CLEAR", "_q": "clear: comprehensive learning enabled adversarial reconstruction for subtle structure enhanced low-dose ct imaging clear tmi low-dose ct denoising doi.org tmi.2021.3097808" }, { "id": "dan-net", "title": "Dual-Domain Adaptive-Scaling Non-Local Network for CT Metal Artifact Reduction", "year": 2021, "venue": "MICCAI", "preprint": false, "topics": [ "metal-artifact", "unrolling" ], "links": { "paper": "https://doi.org/10.1007/978-3-030-87231-1_24", "code": "https://github.com/zjk1988/DAN-Net" }, "abbr": "DAN-Net", "_q": "dual-domain adaptive-scaling non-local network for ct metal artifact reduction dan-net miccai metal artifact reduction deep unrolling & model-based learning doi.org 978-3-030-87231-1_24 github.com dan-net" }, { "id": "dctr", "title": "Dynamic CT Reconstruction From Limited Views With Implicit Neural Representations", "year": 2021, "venue": "ICCV", "preprint": false, "topics": [ "inr", "dynamic", "limited-angle" ], "links": { "paper": "https://doi.org/10.1109/iccv48922.2021.00226" }, "abbr": "DCTR", "_q": "dynamic ct reconstruction from limited views with implicit neural representations dctr iccv implicit neural representations dynamic & 4d ct limited-angle tomography doi.org iccv48922.2021.00226" }, { "id": "deacnn", "title": "Learning a Deep CNN Denoising Approach Using Anatomical Prior Information Implemented With Attention Mechanism for Low-Dose CT Imaging on Clinical Patient Data From Multiple Anatomical Sites", "year": 2021, "venue": "JBHI", "preprint": false, "topics": [ "low-dose", "unrolling" ], "links": { "paper": "https://doi.org/10.1109/jbhi.2021.3061758" }, "abbr": "DeACNN", "_q": "learning a deep cnn denoising approach using anatomical prior information implemented with attention mechanism for low-dose ct imaging on clinical patient data from multiple anatomical sites deacnn jbhi low-dose ct denoising deep unrolling & model-based learning doi.org jbhi.2021.3061758" }, { "id": "drone", "title": "DRONE: Dual-Domain Residual-Based Optimization Network for Sparse-View CT Reconstruction", "year": 2021, "venue": "TMI", "preprint": false, "topics": [ "sparse-view", "unrolling" ], "links": { "paper": "https://doi.org/10.1109/tmi.2021.3078067", "code": "https://github.com/weiwenwu12/DRONE" }, "abbr": "DRONE", "_q": "drone: dual-domain residual-based optimization network for sparse-view ct reconstruction drone tmi sparse-view ct deep unrolling & model-based learning doi.org tmi.2021.3078067 github.com drone" }, { "id": "dsignet", "title": "Downsampled Imaging Geometric Modeling for Accurate CT Reconstruction via Deep Learning", "year": 2021, "venue": "TMI", "preprint": false, "topics": [ "geometry", "unrolling" ], "links": { "paper": "https://doi.org/10.1109/tmi.2021.3074783", "code": "https://github.com/hejipro/DSigNet" }, "abbr": "DSigNet", "_q": "downsampled imaging geometric modeling for accurate ct reconstruction via deep learning dsignet tmi geometry calibration & motion compensation deep unrolling & model-based learning doi.org tmi.2021.3074783 github.com dsignet" }, { "id": "fdm", "title": "Degradation-Aware Deep Learning Framework for Sparse-View CT Reconstruction", "year": 2021, "venue": "Tomography", "preprint": false, "topics": [ "sparse-view" ], "links": { "paper": "https://doi.org/10.3390/tomography7040077", "code": "https://github.com/sunchang2017/degradation-aware-sparse-CT-reconstruction" }, "abbr": "FDM", "_q": "degradation-aware deep learning framework for sparse-view ct reconstruction fdm tomography sparse-view ct doi.org tomography7040077 github.com degradation-aware-sparse-ct-reconstruction" }, { "id": "fista-net", "title": "FISTA-Net: Learning a Fast Iterative Shrinkage Thresholding Network for Inverse Problems in Imaging", "year": 2021, "venue": "TMI", "preprint": false, "topics": [ "unrolling", "classical" ], "links": { "paper": "https://doi.org/10.1109/tmi.2021.3054167", "code": "https://github.com/jinxixiang/FISTA-Net" }, "abbr": "FISTA-Net", "_q": "fista-net: learning a fast iterative shrinkage thresholding network for inverse problems in imaging fista-net tmi deep unrolling & model-based learning classical & iterative reconstruction doi.org tmi.2021.3054167 github.com fista-net" }, { "id": "indudonet", "title": "An Interpretable Dual Domain Network for CT Metal Artifact Reduction", "year": 2021, "venue": "MICCAI", "preprint": false, "topics": [ "metal-artifact", "unrolling" ], "links": { "paper": "https://arxiv.org/abs/2109.05298", "code": "https://github.com/hongwang01/InDuDoNet" }, "abbr": "InDuDoNet", "_q": "an interpretable dual domain network for ct metal artifact reduction indudonet miccai metal artifact reduction deep unrolling & model-based learning arxiv.org 2109.05298 github.com indudonet" }, { "id": "intratomo", "title": "IntraTomo: Self-supervised Learning-based Tomography via Sinogram Synthesis and Prediction", "year": 2021, "venue": "ICCV", "preprint": false, "topics": [ "self-supervised" ], "links": { "paper": "https://doi.org/10.1109/iccv48922.2021.00197", "code": "https://github.com/vccimaging/IntraTomo" }, "abbr": "IntraTomo", "_q": "intratomo: self-supervised learning-based tomography via sinogram synthesis and prediction intratomo iccv self-supervised & untrained methods doi.org iccv48922.2021.00197 github.com intratomo" }, { "id": "lmfi", "title": "Learnable Multi-scale Fourier Interpolation for Sparse View CT Image Reconstruction", "year": 2021, "venue": "MICCAI", "preprint": false, "topics": [ "sparse-view" ], "links": { "paper": "https://doi.org/10.1007/978-3-030-87231-1_28" }, "abbr": "LMFI", "_q": "learnable multi-scale fourier interpolation for sparse view ct image reconstruction lmfi miccai sparse-view ct doi.org 978-3-030-87231-1_28" }, { "id": "magic", "title": "MAGIC: Manifold and graph integrative convolutional network for low-dose CT reconstruction", "year": 2021, "venue": "TMI", "preprint": false, "topics": [ "low-dose" ], "links": { "paper": "https://arxiv.org/abs/2008.00406" }, "abbr": "MAGIC", "_q": "magic: manifold and graph integrative convolutional network for low-dose ct reconstruction magic tmi low-dose ct denoising arxiv.org 2008.00406" }, { "id": "map-nn", "title": "Competitive performance of a modularized deep neural network compared to commercial algorithms for low-dose CT image reconstruction", "year": 2021, "venue": "Nat Mach Intell", "preprint": false, "topics": [ "low-dose" ], "links": { "paper": "https://doi.org/10.1038/s42256-019-0057-9" }, "abbr": "MAP-NN", "_q": "competitive performance of a modularized deep neural network compared to commercial algorithms for low-dose ct image reconstruction map-nn nat mach intell low-dose ct denoising doi.org s42256-019-0057-9" }, { "id": "metainv-net", "title": "MetaInv-Net: Meta Inversion Network for Sparse View CT Image Reconstruction", "year": 2021, "venue": "TMI", "preprint": false, "topics": [ "sparse-view", "unrolling" ], "links": { "paper": "https://doi.org/10.1109/tmi.2020.3033541", "code": "https://github.com/haimiaozh/MetaInv-Net" }, "abbr": "MetaInv-Net", "_q": "metainv-net: meta inversion network for sparse view ct image reconstruction metainv-net tmi sparse-view ct deep unrolling & model-based learning doi.org tmi.2020.3033541 github.com metainv-net" }, { "id": "n2s", "title": "Self-Supervised Training For Low-Dose Ct Reconstruction", "year": 2021, "venue": "ISBI", "preprint": false, "topics": [ "low-dose", "self-supervised" ], "links": { "paper": "https://doi.org/10.1109/isbi48211.2021.9433944" }, "abbr": "N2S", "_q": "self-supervised training for low-dose ct reconstruction n2s isbi low-dose ct denoising self-supervised & untrained methods doi.org isbi48211.2021.9433944" }, { "id": "pdf", "title": "CT Reconstruction With PDF: Parameter-Dependent Framework for Data From Multiple Geometries and Dose Levels", "year": 2021, "venue": "TMI", "preprint": false, "topics": [ "geometry", "unrolling" ], "links": { "paper": "https://doi.org/10.1109/tmi.2021.3085839" }, "abbr": "PDF", "_q": "ct reconstruction with pdf: parameter-dependent framework for data from multiple geometries and dose levels pdf tmi geometry calibration & motion compensation deep unrolling & model-based learning doi.org tmi.2021.3085839" }, { "id": "sinonet", "title": "Noise-Generating-Mechanism-Driven Unsupervised Learning for Low-Dose CT Sinogram Recovery", "year": 2021, "venue": "TRPMS", "preprint": false, "topics": [ "low-dose", "self-supervised" ], "links": { "paper": "https://doi.org/10.1109/trpms.2021.3083361" }, "abbr": "SinoNet", "_q": "noise-generating-mechanism-driven unsupervised learning for low-dose ct sinogram recovery sinonet trpms low-dose ct denoising self-supervised & untrained methods doi.org trpms.2021.3083361" }, { "id": "super", "title": "Unified Supervised-Unsupervised (SUPER) Learning for X-ray CT Image Reconstruction", "year": 2021, "venue": "TMI", "preprint": false, "topics": [ "self-supervised" ], "links": { "paper": "https://arxiv.org/abs/2010.02761" }, "abbr": "SUPER", "_q": "unified supervised-unsupervised (super) learning for x-ray ct image reconstruction super tmi self-supervised & untrained methods arxiv.org 2010.02761" }, { "id": "tensor-net", "title": "Learning to Reconstruct CT Images From the VVBP-Tensor", "year": 2021, "venue": "TMI", "preprint": false, "topics": [ "unrolling", "classical" ], "links": { "paper": "https://doi.org/10.1109/tmi.2021.3090257" }, "abbr": "Tensor-Net", "_q": "learning to reconstruct ct images from the vvbp-tensor tensor-net tmi deep unrolling & model-based learning classical & iterative reconstruction doi.org tmi.2021.3090257" }, { "id": "2-step-sparse-view-ct-reconstruction-with-a-domain-specifi", "title": "2-Step Sparse-View CT Reconstruction with a Domain-Specific Perceptual Network", "year": 2020, "venue": null, "preprint": true, "topics": [ "sparse-view" ], "links": { "paper": "https://arxiv.org/abs/2012.04743" }, "_q": "2-step sparse-view ct reconstruction with a domain-specific perceptual network preprint sparse-view ct arxiv.org 2012.04743" }, { "id": "a-review-on-deep-learning-in-medical-image-reconstruction", "title": "A review on deep learning in medical image reconstruction", "year": 2020, "venue": "JORSC", "preprint": false, "topics": [ "survey", "unrolling" ], "links": { "paper": "https://arxiv.org/abs/1906.10643" }, "_q": "a review on deep learning in medical image reconstruction jorsc surveys & reviews deep unrolling & model-based learning arxiv.org 1906.10643" }, { "id": "cadl", "title": "Noise and spatial resolution properties of a commercially available deep learning‐based CT reconstruction algorithm", "year": 2020, "venue": "Med Phys", "preprint": false, "topics": [ "low-dose" ], "links": { "paper": "https://doi.org/10.1002/mp.14319" }, "abbr": "CADL", "_q": "noise and spatial resolution properties of a commercially available deep learning‐based ct reconstruction algorithm cadl med phys low-dose ct denoising doi.org mp.14319" }, { "id": "deer", "title": "Deep efficient end-to-end reconstruction (DEER) network for few-view breast CT image reconstruction", "year": 2020, "venue": "IEEE Access", "preprint": false, "topics": [ "sparse-view" ], "links": { "paper": "https://doi.org/10.1109/access.2020.3033795", "code": "https://github.com/WANG-AXIS/DEER" }, "abbr": "DEER", "_q": "deep efficient end-to-end reconstruction (deer) network for few-view breast ct image reconstruction deer ieee access sparse-view ct doi.org access.2020.3033795 github.com deer" }, { "id": "dip", "title": "Computed Tomography Reconstruction Using Deep Image Prior and Learned Reconstruction Methods", "year": 2020, "venue": "Inverse Problems", "preprint": false, "topics": [ "self-supervised" ], "links": { "paper": "https://doi.org/10.1088/1361-6420/aba415", "code": "https://github.com/oterobaguer/dip-ct-benchmark" }, "abbr": "DIP", "_q": "computed tomography reconstruction using deep image prior and learned reconstruction methods dip inverse problems self-supervised & untrained methods doi.org aba415 github.com dip-ct-benchmark" }, { "id": "dl-ct-rev", "title": "Deep Learning for Tomographic Image Reconstruction", "year": 2020, "venue": "Nat Mach Intell", "preprint": false, "topics": [ "survey" ], "links": { "paper": "https://doi.org/10.1038/s42256-020-00273-z" }, "abbr": "DL-CT-Rev", "_q": "deep learning for tomographic image reconstruction dl-ct-rev nat mach intell surveys & reviews doi.org s42256-020-00273-z" }, { "id": "dl-invprob", "title": "Deep Learning Techniques for Inverse Problems in Imaging", "year": 2020, "venue": "IEEE JSAIT", "preprint": false, "topics": [ "survey", "unrolling" ], "links": { "paper": "https://arxiv.org/abs/2005.06001" }, "abbr": "DL-InvProb", "_q": "deep learning techniques for inverse problems in imaging dl-invprob ieee jsait surveys & reviews deep unrolling & model-based learning arxiv.org 2005.06001" }, { "id": "dlmir", "title": "Deep learning methods for image reconstruction from angularly sparse data for CT and SAR imaging", "year": 2020, "venue": "ASARI", "preprint": false, "topics": [ "sparse-view" ], "links": { "paper": "https://doi.org/10.1117/12.2558953", "code": "https://github.com/e-yavuz/Deep-Learning-Methods-for-Image-Reconstruction-from-Angularly-Sparse-Data-for-CT-and-SAR-Imaging" }, "abbr": "DLMIR", "_q": "deep learning methods for image reconstruction from angularly sparse data for ct and sar imaging dlmir asari sparse-view ct doi.org 12.2558953 github.com deep-learning-methods-for-image-reconstruction-from-angularly-sparse-data-for-ct-and-sar-imaging" }, { "id": "edcnn", "title": "EDCNN: Edge Enhancement-Based Densely Connected Network with Compound Loss for Low-Dose CT Denoising", "year": 2020, "venue": "ICSP", "preprint": false, "topics": [ "low-dose" ], "links": { "paper": "https://doi.org/10.1109/icsp48669.2020.9320928", "code": "https://github.com/workingcoder/EDCNN" }, "abbr": "EDCNN", "_q": "edcnn: edge enhancement-based densely connected network with compound loss for low-dose ct denoising edcnn icsp low-dose ct denoising doi.org icsp48669.2020.9320928 github.com edcnn" }, { "id": "etedn", "title": "An End-to-End Deep Network for Reconstructing CT Images Directly From Sparse Sinograms", "year": 2020, "venue": "TCI", "preprint": false, "topics": [ "sparse-view", "unrolling" ], "links": { "paper": "https://doi.org/10.1109/tci.2020.3039385", "code": "https://github.com/wangwei-cmd/CT-image-reconstruction" }, "abbr": "ETEDN", "_q": "an end-to-end deep network for reconstructing ct images directly from sparse sinograms etedn tci sparse-view ct deep unrolling & model-based learning doi.org tci.2020.3039385 github.com ct-image-reconstruction" }, { "id": "fstensor", "title": "FSTensorFull-spectrum-knowledge-aware tensor model for energy-resolved CT iterative reconstruction", "year": 2020, "venue": "TMI", "preprint": false, "topics": [ "classical" ], "links": { "paper": "https://doi.org/10.1109/tmi.2020.2976692" }, "abbr": "FSTensor", "_q": "fstensorfull-spectrum-knowledge-aware tensor model for energy-resolved ct iterative reconstruction fstensor tmi classical & iterative reconstruction doi.org tmi.2020.2976692" }, { "id": "hd-cnn", "title": "Artifact removal using a hybrid-domain convolutional neural network for limited-angle computed tomography imaging", "year": 2020, "venue": "PMB", "preprint": false, "topics": [ "limited-angle", "unrolling" ], "links": { "paper": "https://doi.org/10.1088/1361-6560/ab9066" }, "abbr": "HD-CNN", "_q": "artifact removal using a hybrid-domain convolutional neural network for limited-angle computed tomography imaging hd-cnn pmb limited-angle tomography deep unrolling & model-based learning doi.org ab9066" }, { "id": "hdnet", "title": "Hybrid-domain neural network processing for sparse-view CT reconstruction", "year": 2020, "venue": "TRPMS", "preprint": false, "topics": [ "sparse-view" ], "links": { "paper": "https://doi.org/10.1109/trpms.2020.3011413" }, "abbr": "HDNet", "_q": "hybrid-domain neural network processing for sparse-view ct reconstruction hdnet trpms sparse-view ct doi.org trpms.2020.3011413" }, { "id": "iradonmap", "title": "Radon Inversion via Deep Learning", "year": 2020, "venue": "TMI", "preprint": false, "topics": [ "unrolling", "classical" ], "links": { "paper": "https://arxiv.org/abs/1808.03015" }, "abbr": "iRadonMAP", "_q": "radon inversion via deep learning iradonmap tmi deep unrolling & model-based learning classical & iterative reconstruction arxiv.org 1808.03015" }, { "id": "learned-convex-regularizers-for-inverse-problems", "title": "Learned convex regularizers for inverse problems", "year": 2020, "venue": null, "preprint": true, "topics": [ "classical", "unrolling" ], "links": { "paper": "https://arxiv.org/abs/2008.02839" }, "_q": "learned convex regularizers for inverse problems preprint classical & iterative reconstruction deep unrolling & model-based learning arxiv.org 2008.02839" }, { "id": "limited-view-tomographic-reconstruction-using-a-deep-recur", "title": "Limited View Tomographic Reconstruction Using a Deep Recurrent Framework with Residual Dense Spatial-Channel Attention Network and Sinogram Consistency", "year": 2020, "venue": null, "preprint": true, "topics": [ "limited-angle", "unrolling" ], "links": { "paper": "https://arxiv.org/abs/2009.01782" }, "_q": "limited view tomographic reconstruction using a deep recurrent framework with residual dense spatial-channel attention network and sinogram consistency preprint limited-angle tomography deep unrolling & model-based learning arxiv.org 2009.01782" }, { "id": "lrtp", "title": "Spectral CT reconstruction via low-rank representation and region-specific texture preserving Markov random field regularization", "year": 2020, "venue": "TMI", "preprint": false, "topics": [ "spectral" ], "links": { "paper": "https://doi.org/10.1109/tmi.2020.2983414" }, "abbr": "LRTP", "_q": "spectral ct reconstruction via low-rank representation and region-specific texture preserving markov random field regularization lrtp tmi spectral & dual-energy ct doi.org tmi.2020.2983414" }, { "id": "momentum-net", "title": "Momentum-Net: Fast and convergent iterative neural network for inverse problems", "year": 2020, "venue": "TPAMI", "preprint": false, "topics": [ "unrolling", "classical" ], "links": { "paper": "https://doi.org/10.1109/tpami.2020.3012955" }, "abbr": "Momentum-Net", "_q": "momentum-net: fast and convergent iterative neural network for inverse problems momentum-net tpami deep unrolling & model-based learning classical & iterative reconstruction doi.org tpami.2020.3012955" }, { "id": "redaep", "title": "REDAEP: Robust and Enhanced Denoising Autoencoding Prior for Sparse-View CT Reconstruction", "year": 2020, "venue": "TRPMS", "preprint": false, "topics": [ "sparse-view", "low-dose" ], "links": { "paper": "https://doi.org/10.1109/trpms.2020.2989634" }, "abbr": "REDAEP", "_q": "redaep: robust and enhanced denoising autoencoding prior for sparse-view ct reconstruction redaep trpms sparse-view ct low-dose ct denoising doi.org trpms.2020.2989634" }, { "id": "sacnn", "title": "SACNN: Self-Attention Convolutional Neural Network for Low-Dose CT Denoising With Self-Supervised Perceptual Loss Network", "year": 2020, "venue": "TMI", "preprint": false, "topics": [ "low-dose", "self-supervised", "unrolling" ], "links": { "paper": "https://doi.org/10.1109/tmi.2020.2968472" }, "abbr": "SACNN", "_q": "sacnn: self-attention convolutional neural network for low-dose ct denoising with self-supervised perceptual loss network sacnn tmi low-dose ct denoising self-supervised & untrained methods deep unrolling & model-based learning doi.org tmi.2020.2968472" }, { "id": "sparsity2dl", "title": "Image Reconstruction: From Sparsity to Data-Adaptive Methods and Machine Learning", "year": 2020, "venue": "Proc. IEEE", "preprint": false, "topics": [ "survey", "classical" ], "links": { "paper": "https://doi.org/10.1109/JPROC.2019.2936204" }, "abbr": "Sparsity2DL", "_q": "image reconstruction: from sparsity to data-adaptive methods and machine learning sparsity2dl proc. ieee surveys & reviews classical & iterative reconstruction doi.org jproc.2019.2936204" }, { "id": "tvwfr", "title": "Sparse View CT Image Reconstruction Based on Total Variation and Wavelet Frame Regularization", "year": 2020, "venue": "IEEE Access", "preprint": false, "topics": [ "sparse-view", "classical" ], "links": { "paper": "https://doi.org/10.1109/access.2020.2982229" }, "abbr": "TVWFR", "_q": "sparse view ct image reconstruction based on total variation and wavelet frame regularization tvwfr ieee access sparse-view ct classical & iterative reconstruction doi.org access.2020.2982229" }, { "id": "dl", "title": "Limited-Angle X-Ray CT Reconstruction Using Image Gradient ℓ₀-Norm With Dictionary Learning", "year": 2020, "venue": "TRPMS", "preprint": false, "topics": [ "limited-angle" ], "links": { "paper": "https://doi.org/10.1109/trpms.2020.2991887" }, "abbr": "ℓ₀DL", "_q": "limited-angle x-ray ct reconstruction using image gradient ℓ₀-norm with dictionary learning ℓ₀dl trpms limited-angle tomography doi.org trpms.2020.2991887" }, { "id": "ct-evolution", "title": "The Evolution of Image Reconstruction for CT: From Filtered Back Projection to Artificial Intelligence", "year": 2019, "venue": "Eur Radiol", "preprint": false, "topics": [ "survey", "classical" ], "links": { "paper": "https://doi.org/10.1007/s00330-018-5810-7" }, "abbr": "CT-Evolution", "_q": "the evolution of image reconstruction for ct: from filtered back projection to artificial intelligence ct-evolution eur radiol surveys & reviews classical & iterative reconstruction doi.org s00330-018-5810-7" }, { "id": "datadriven", "title": "Solving Inverse Problems Using Data-Driven Models", "year": 2019, "venue": "Acta Numerica", "preprint": false, "topics": [ "survey", "classical" ], "links": { "paper": "https://doi.org/10.1017/S0962492919000059" }, "abbr": "DataDriven", "_q": "solving inverse problems using data-driven models datadriven acta numerica surveys & reviews classical & iterative reconstruction doi.org s0962492919000059" }, { "id": "dl-piccs", "title": "Accurate and robust sparse-view angle CT image reconstruction using deep learning and prior image constrained compressed sensing (DL-PICCS)", "year": 2019, "venue": "Med Phys", "preprint": false, "topics": [ "sparse-view", "classical" ], "links": { "paper": "https://doi.org/10.1002/mp.15183" }, "abbr": "DL-PICCS", "_q": "accurate and robust sparse-view angle ct image reconstruction using deep learning and prior image constrained compressed sensing (dl-piccs) dl-piccs med phys sparse-view ct classical & iterative reconstruction doi.org mp.15183" }, { "id": "dnnss", "title": "Deep-neural-network-based sinogram synthesis for sparse-view CT image reconstruction", "year": 2019, "venue": "TRPMS", "preprint": false, "topics": [ "sparse-view" ], "links": { "paper": "https://doi.org/10.1109/trpms.2018.2867611" }, "abbr": "DNNSS", "_q": "deep-neural-network-based sinogram synthesis for sparse-view ct image reconstruction dnnss trpms sparse-view ct doi.org trpms.2018.2867611" }, { "id": "extreme-few-view-ct-reconstruction-using-deep-inference", "title": "Extreme Few-view CT Reconstruction using Deep Inference", "year": 2019, "venue": null, "preprint": true, "topics": [ "sparse-view" ], "links": { "paper": "https://arxiv.org/abs/1910.05375" }, "_q": "extreme few-view ct reconstruction using deep inference preprint sparse-view ct arxiv.org 1910.05375" }, { "id": "ictnet", "title": "Sinogram interpolation for sparse-view micro-CT with deep learning neural network", "year": 2019, "venue": "SPIE MI", "preprint": false, "topics": [ "sparse-view" ], "links": { "paper": "https://arxiv.org/abs/1902.03362", "code": "https://github.com/Swapneel7/Sparse-CT-Reconstruction-using-Deep-learning" }, "abbr": "iCTNet", "_q": "sinogram interpolation for sparse-view micro-ct with deep learning neural network ictnet spie mi sparse-view ct arxiv.org 1902.03362 github.com sparse-ct-reconstruction-using-deep-learning" }, { "id": "pde", "title": "A regional adaptive variational PDE model for computed tomography image reconstruction", "year": 2019, "venue": "PR", "preprint": false, "topics": [ "classical" ], "links": { "paper": "https://doi.org/10.1016/j.patcog.2019.03.009" }, "abbr": "PDE", "_q": "a regional adaptive variational pde model for computed tomography image reconstruction pde pr classical & iterative reconstruction doi.org j.patcog.2019.03.009" }, { "id": "psrv", "title": "Patient-specific reconstruction of volumetric computed tomography images from a single projection view via deep learning", "year": 2019, "venue": "Nat Biomed Eng", "preprint": false, "topics": [ "sparse-view", "classical" ], "links": { "paper": "https://doi.org/10.1038/s41551-019-0466-4" }, "abbr": "PSRV", "_q": "patient-specific reconstruction of volumetric computed tomography images from a single projection view via deep learning psrv nat biomed eng sparse-view ct classical & iterative reconstruction doi.org s41551-019-0466-4" }, { "id": "maier-2019", "title": "Real-Time Scatter Estimation for Medical CT Using the Deep Scatter Estimation: Method and Robustness Analysis with Respect to Different Anatomies, Dose Levels, Tube Voltages, and Data Truncation", "year": 2019, "venue": "Med Phys", "preprint": false, "topics": [ "scatter" ], "links": { "paper": "https://doi.org/10.1002/mp.13274" }, "_q": "real-time scatter estimation for medical ct using the deep scatter estimation: method and robustness analysis with respect to different anatomies, dose levels, tube voltages, and data truncation med phys scatter correction doi.org mp.13274" }, { "id": "sisvm", "title": "Learning to Reconstruct Computed Tomography Images Directly From Sinogram Data Under A Variety of Data Acquisition Conditions", "year": 2019, "venue": "TMI", "preprint": false, "topics": [ "unrolling", "classical" ], "links": { "paper": "https://doi.org/10.1109/tmi.2019.2910760" }, "abbr": "SISVM", "_q": "learning to reconstruct computed tomography images directly from sinogram data under a variety of data acquisition conditions sisvm tmi deep unrolling & model-based learning classical & iterative reconstruction doi.org tmi.2019.2910760" }, { "id": "spss", "title": "Sharpness preserved sinogram synthesis using convolutional neural network for sparse-view CT imaging", "year": 2019, "venue": "SPIE MI", "preprint": false, "topics": [ "sparse-view", "unrolling" ], "links": { "paper": "https://doi.org/10.1117/12.2512894" }, "abbr": "SPSS", "_q": "sharpness preserved sinogram synthesis using convolutional neural network for sparse-view ct imaging spss spie mi sparse-view ct deep unrolling & model-based learning doi.org 12.2512894" }, { "id": "spultra", "title": "SPULTRA: Low-Dose CT Image Reconstruction with Joint Statistical and Learned Image Models", "year": 2019, "venue": "TMI", "preprint": false, "topics": [ "low-dose" ], "links": { "paper": "https://doi.org/10.1109/tmi.2019.2934933" }, "abbr": "SPULTRA", "_q": "spultra: low-dose ct image reconstruction with joint statistical and learned image models spultra tmi low-dose ct denoising doi.org tmi.2019.2934933" }, { "id": "super-2", "title": "SUPER Learning: A Supervised-Unsupervised Framework for Low-Dose CT Image Reconstruction", "year": 2019, "venue": "ICCVW", "preprint": false, "topics": [ "low-dose", "self-supervised" ], "links": { "paper": "https://doi.org/10.1109/iccvw.2019.00490" }, "abbr": "SUPER-2", "_q": "super learning: a supervised-unsupervised framework for low-dose ct image reconstruction super-2 iccvw low-dose ct denoising self-supervised & untrained methods doi.org iccvw.2019.00490" }, { "id": "vvbp-tsvd", "title": "VVBP-Tensor in the FBP Algorithm: Its Properties and Application in Low-Dose CT Reconstruction", "year": 2019, "venue": "TMI", "preprint": false, "topics": [ "low-dose", "classical" ], "links": { "paper": "https://doi.org/10.1109/tmi.2019.2935187" }, "abbr": "VVBP-tSVD", "_q": "vvbp-tensor in the fbp algorithm: its properties and application in low-dose ct reconstruction vvbp-tsvd tmi low-dose ct denoising classical & iterative reconstruction doi.org tmi.2019.2935187" }, { "id": "3padmm", "title": "Optimizing a parameterized plug-and-play ADMM for iterative low-dose CT reconstruction", "year": 2018, "venue": "TMI", "preprint": false, "topics": [ "low-dose" ], "links": { "paper": "https://doi.org/10.1109/tmi.2018.2865202" }, "abbr": "3pADMM", "_q": "optimizing a parameterized plug-and-play admm for iterative low-dose ct reconstruction 3padmm tmi low-dose ct denoising doi.org tmi.2018.2865202" }, { "id": "automap", "title": "Image reconstruction by domain-transform manifold learning", "year": 2018, "venue": "Nature", "preprint": false, "topics": [ "unrolling", "classical" ], "links": { "paper": "https://doi.org/10.1038/nature25988" }, "abbr": "AUTOMAP", "_q": "image reconstruction by domain-transform manifold learning automap nature deep unrolling & model-based learning classical & iterative reconstruction doi.org nature25988" }, { "id": "cnnrpgd", "title": "CNN-Based Projected Gradient Descent for Consistent CT Image Reconstruction", "year": 2018, "venue": "TMI", "preprint": false, "topics": [ "unrolling" ], "links": { "paper": "https://doi.org/10.1109/tmi.2018.2832656" }, "abbr": "CNNRPGD", "_q": "cnn-based projected gradient descent for consistent ct image reconstruction cnnrpgd tmi deep unrolling & model-based learning doi.org tmi.2018.2832656" }, { "id": "ctnet", "title": "Lose The Views: Limited Angle CT Reconstruction via Implicit Sinogram Completion", "year": 2018, "venue": "CVPR", "preprint": false, "topics": [ "limited-angle" ], "links": { "paper": "https://doi.org/10.1109/cvpr.2018.00664" }, "abbr": "CTNet", "_q": "lose the views: limited angle ct reconstruction via implicit sinogram completion ctnet cvpr limited-angle tomography doi.org cvpr.2018.00664" }, { "id": "dd-net", "title": "A Sparse-View CT Reconstruction Method Based on Combination of DenseNet and Deconvolution", "year": 2018, "venue": "TMI", "preprint": false, "topics": [ "sparse-view", "unrolling" ], "links": { "paper": "https://doi.org/10.1109/tmi.2018.2823338", "code": "https://github.com/zzc623/DD_Net" }, "abbr": "DD-Net", "_q": "a sparse-view ct reconstruction method based on combination of densenet and deconvolution dd-net tmi sparse-view ct deep unrolling & model-based learning doi.org tmi.2018.2823338 github.com dd_net" }, { "id": "dlct", "title": "Deep Learning Computed Tomography: Learning Projection-Domain Weights From Image Domain in Limited Angle Problems", "year": 2018, "venue": "TMI", "preprint": false, "topics": [ "limited-angle" ], "links": { "paper": "https://doi.org/10.1109/tmi.2018.2833499" }, "abbr": "DLCT", "_q": "deep learning computed tomography: learning projection-domain weights from image domain in limited angle problems dlct tmi limited-angle tomography doi.org tmi.2018.2833499" }, { "id": "dse", "title": "Deep Scatter Estimation (DSE): Feasibility of Using a Deep Convolutional Neural Network for Scatter Estimation in X-Ray Computed Tomography", "year": 2018, "venue": "SPIE MI", "preprint": false, "topics": [ "scatter", "unrolling" ], "links": { "paper": "https://doi.org/10.1117/12.2292919" }, "abbr": "DSE", "_q": "deep scatter estimation (dse): feasibility of using a deep convolutional neural network for scatter estimation in x-ray computed tomography dse spie mi scatter correction deep unrolling & model-based learning doi.org 12.2292919" }, { "id": "learn", "title": "LEARN: Learned Experts’ Assessment-Based Reconstruction Network for Sparse-Data CT", "year": 2018, "venue": "TMI", "preprint": false, "topics": [ "unrolling" ], "links": { "paper": "https://doi.org/10.1109/tmi.2018.2805692" }, "abbr": "LEARN", "_q": "learn: learned experts’ assessment-based reconstruction network for sparse-data ct learn tmi deep unrolling & model-based learning doi.org tmi.2018.2805692" }, { "id": "lpd", "title": "Learned Primal-Dual Reconstruction", "year": 2018, "venue": "TMI", "preprint": false, "topics": [ "unrolling" ], "links": { "paper": "https://doi.org/10.1109/tmi.2018.2799231" }, "abbr": "LPD", "_q": "learned primal-dual reconstruction lpd tmi deep unrolling & model-based learning doi.org tmi.2018.2799231" }, { "id": "nlctf", "title": "Non-Local Low-Rank Cube-Based Tensor Factorization for Spectral CT Reconstruction", "year": 2018, "venue": "TMI", "preprint": false, "topics": [ "spectral" ], "links": { "paper": "https://doi.org/10.1109/tmi.2018.2878226" }, "abbr": "NLCTF", "_q": "non-local low-rank cube-based tensor factorization for spectral ct reconstruction nlctf tmi spectral & dual-energy ct doi.org tmi.2018.2878226" }, { "id": "ptpn", "title": "Intelligent Parameter Tuning in Optimization-Based Iterative CT Reconstruction via Deep Reinforcement Learning", "year": 2018, "venue": "TMI", "preprint": false, "topics": [ "classical", "unrolling" ], "links": { "paper": "https://doi.org/10.1109/tmi.2018.2823679" }, "abbr": "PTPN", "_q": "intelligent parameter tuning in optimization-based iterative ct reconstruction via deep reinforcement learning ptpn tmi classical & iterative reconstruction deep unrolling & model-based learning doi.org tmi.2018.2823679" }, { "id": "rad", "title": "Regularization analysis and design for prior-image-based X-ray CT reconstruction", "year": 2018, "venue": "TMI", "preprint": false, "topics": [ "classical" ], "links": { "paper": "https://doi.org/10.1109/tmi.2018.2847250" }, "abbr": "RAD", "_q": "regularization analysis and design for prior-image-based x-ray ct reconstruction rad tmi classical & iterative reconstruction doi.org tmi.2018.2847250" }, { "id": "sagan", "title": "Sharpness-Aware Low Dose CT Denoising Using Conditional Generative Adversarial Network", "year": 2018, "venue": "JDI", "preprint": false, "topics": [ "low-dose" ], "links": { "paper": "https://doi.org/10.1007/s10278-018-0056-0", "code": "https://github.com/xinario/SAGAN" }, "abbr": "SAGAN", "_q": "sharpness-aware low dose ct denoising using conditional generative adversarial network sagan jdi low-dose ct denoising doi.org s10278-018-0056-0 github.com sagan" }, { "id": "statistical-image-reconstruction-using-mixed-poisson-gauss", "title": "Statistical Image Reconstruction Using Mixed Poisson-Gaussian Noise Model for X-Ray CT", "year": 2018, "venue": null, "preprint": true, "topics": [ "classical", "low-dose" ], "links": { "paper": "https://arxiv.org/abs/1801.09533" }, "_q": "statistical image reconstruction using mixed poisson-gaussian noise model for x-ray ct preprint classical & iterative reconstruction low-dose ct denoising arxiv.org 1801.09533" }, { "id": "tfu-net", "title": "Framing U-Net via Deep Convolutional Framelets - Application to Sparse-view CT", "year": 2018, "venue": "TMI", "preprint": false, "topics": [ "sparse-view" ], "links": { "paper": "https://arxiv.org/abs/1708.08333" }, "abbr": "TFU-Net", "_q": "framing u-net via deep convolutional framelets - application to sparse-view ct tfu-net tmi sparse-view ct arxiv.org 1708.08333" }, { "id": "wavresnet", "title": "Deep Convolutional Framelet Denosing for Low-Dose CT via Wavelet Residual Network", "year": 2018, "venue": "TMI", "preprint": false, "topics": [ "low-dose" ], "links": { "paper": "https://arxiv.org/abs/1707.09938" }, "abbr": "WavResNet", "_q": "deep convolutional framelet denosing for low-dose ct via wavelet residual network wavresnet tmi low-dose ct denoising arxiv.org 1707.09938" }, { "id": "wgan-vgg", "title": "Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Loss", "year": 2018, "venue": "TMI", "preprint": false, "topics": [ "low-dose" ], "links": { "paper": "https://doi.org/10.1109/tmi.2018.2827462", "code": "https://github.com/SSinyu/WGAN-VGG" }, "abbr": "WGAN-VGG", "_q": "low dose ct image denoising using a generative adversarial network with wasserstein distance and perceptual loss wgan-vgg tmi low-dose ct denoising doi.org tmi.2018.2827462 github.com wgan-vgg" }, { "id": "cnn-invrev", "title": "Convolutional Neural Networks for Inverse Problems in Imaging: A Review", "year": 2017, "venue": "IEEE SPM", "preprint": false, "topics": [ "survey" ], "links": { "paper": "https://doi.org/10.1109/MSP.2017.2739299" }, "abbr": "CNN-InvRev", "_q": "convolutional neural networks for inverse problems in imaging: a review cnn-invrev ieee spm surveys & reviews doi.org msp.2017.2739299" }, { "id": "deepcnn", "title": "A deep convolutional neural network using directional wavelets for low‐dose X‐ray CT reconstruction", "year": 2017, "venue": "Med Phys", "preprint": false, "topics": [ "unrolling" ], "links": { "paper": "https://arxiv.org/abs/1610.09736" }, "abbr": "DeepCNN", "_q": "a deep convolutional neural network using directional wavelets for low‐dose x‐ray ct reconstruction deepcnn med phys deep unrolling & model-based learning arxiv.org 1610.09736" }, { "id": "imap-tv", "title": "Robust low-dose CT sinogram preprocessing via exploiting noise-generating mechanism", "year": 2017, "venue": "TMI", "preprint": false, "topics": [ "low-dose" ], "links": { "paper": "https://doi.org/10.1109/tmi.2017.2767290" }, "abbr": "IMAP-TV", "_q": "robust low-dose ct sinogram preprocessing via exploiting noise-generating mechanism imap-tv tmi low-dose ct denoising doi.org tmi.2017.2767290" }, { "id": "ksae", "title": "Iterative Low-dose CT Reconstruction with Priors Trained by Artificial Neural Network", "year": 2017, "venue": "TMI", "preprint": false, "topics": [ "low-dose" ], "links": { "paper": "https://doi.org/10.1109/tmi.2017.2753138" }, "abbr": "KSAE", "_q": "iterative low-dose ct reconstruction with priors trained by artificial neural network ksae tmi low-dose ct denoising doi.org tmi.2017.2753138" }, { "id": "lodopab-ct", "title": "LoDoPaB-CT, a benchmark dataset for low-dose computed tomography reconstruction (**Scientific Data**) -->", "year": 2017, "venue": "Scientific Data", "preprint": false, "topics": [ "low-dose" ], "links": { "paper": "https://doi.org/10.1038/s41597-021-00893-z", "code": "https://github.com/jleuschn/lodopab_tech_ref" }, "abbr": "LoDoPaB-CT", "_q": "lodopab-ct, a benchmark dataset for low-dose computed tomography reconstruction (**scientific data**) --> lodopab-ct scientific data low-dose ct denoising doi.org s41597-021-00893-z github.com lodopab_tech_ref" }, { "id": "red-cnn", "title": "Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network", "year": 2017, "venue": "TMI", "preprint": false, "topics": [ "low-dose" ], "links": { "paper": "https://doi.org/10.1109/tmi.2017.2715284", "code": "https://github.com/SSinyu/RED-CNN" }, "abbr": "RED-CNN", "_q": "low-dose ct with a residual encoder-decoder convolutional neural network red-cnn tmi low-dose ct denoising doi.org tmi.2017.2715284 github.com red-cnn" }, { "id": "senp", "title": "Low‐dose CT reconstruction using spatially encoded nonlocal penalty", "year": 2017, "venue": "Med Phys", "preprint": false, "topics": [ "classical", "low-dose" ], "links": { "paper": "https://doi.org/10.1002/mp.12523" }, "abbr": "SENP", "_q": "low‐dose ct reconstruction using spatially encoded nonlocal penalty senp med phys classical & iterative reconstruction low-dose ct denoising doi.org mp.12523" }, { "id": "viss", "title": "View-interpolation of sparsely sampled sinogram using convolutional neural network", "year": 2017, "venue": "SPIE MI", "preprint": false, "topics": [ "unrolling" ], "links": { "paper": "https://doi.org/10.1117/12.2254244" }, "abbr": "VISS", "_q": "view-interpolation of sparsely sampled sinogram using convolutional neural network viss spie mi deep unrolling & model-based learning doi.org 12.2254244" }, { "id": "mar-4dec", "title": "Metal Artifact Reduction in CT: Where Are We After Four Decades?", "year": 2016, "venue": "IEEE Access", "preprint": false, "topics": [ "survey", "metal-artifact" ], "links": { "paper": "https://doi.org/10.1109/ACCESS.2016.2608621" }, "abbr": "MAR-4Dec", "_q": "metal artifact reduction in ct: where are we after four decades? mar-4dec ieee access surveys & reviews metal artifact reduction doi.org access.2016.2608621" }, { "id": "mccollough-2015", "title": "Dual- and Multi-Energy CT: Principles, Technical Approaches, and Clinical Applications", "year": 2015, "venue": "Radiology", "preprint": false, "topics": [ "spectral", "survey" ], "links": { "paper": "https://doi.org/10.1148/radiol.2015142631" }, "_q": "dual- and multi-energy ct: principles, technical approaches, and clinical applications radiology spectral & dual-energy ct surveys & reviews doi.org radiol.2015142631" }, { "id": "gao-2012", "title": "4D Cone Beam CT via Spatiotemporal Tensor Framelet", "year": 2012, "venue": "Med Phys", "preprint": false, "topics": [ "dynamic" ], "links": { "paper": "https://doi.org/10.1118/1.4762288" }, "_q": "4d cone beam ct via spatiotemporal tensor framelet med phys dynamic & 4d ct doi.org 1.4762288" }, { "id": "scatter-rev-p2", "title": "A General Framework and Review of Scatter Correction Methods in Cone-Beam CT: Part 2 — Scatter Estimation Approaches", "year": 2011, "venue": "Med Phys", "preprint": false, "topics": [ "scatter", "survey" ], "links": { "paper": "https://doi.org/10.1118/1.3589140" }, "_q": "a general framework and review of scatter correction methods in cone-beam ct: part 2 — scatter estimation approaches med phys scatter correction surveys & reviews doi.org 1.3589140" }, { "id": "scatter-rev", "title": "A General Framework and Review of Scatter Correction Methods in X-Ray Cone-Beam CT: Part 1 — Scatter Compensation Approaches", "year": 2011, "venue": "Med Phys", "preprint": false, "topics": [ "scatter", "survey", "cbct" ], "links": { "paper": "https://doi.org/10.1118/1.3599033" }, "abbr": "Scatter-Rev", "_q": "a general framework and review of scatter correction methods in x-ray cone-beam ct: part 1 — scatter compensation approaches scatter-rev med phys scatter correction surveys & reviews cone-beam ct doi.org 1.3599033" }, { "id": "bergner-2010", "title": "An Investigation of 4D Cone-Beam CT Algorithms for Slowly Rotating Scanners", "year": 2010, "venue": "Med Phys", "preprint": false, "topics": [ "dynamic" ], "links": { "paper": "https://doi.org/10.1118/1.3480986" }, "_q": "an investigation of 4d cone-beam ct algorithms for slowly rotating scanners med phys dynamic & 4d ct doi.org 1.3480986" }, { "id": "rit-2009", "title": "On-the-Fly Motion-Compensated Cone-Beam CT Using an A Priori Model of the Respiratory Motion", "year": 2009, "venue": "Med Phys", "preprint": false, "topics": [ "dynamic" ], "links": { "paper": "https://doi.org/10.1118/1.3115691" }, "_q": "on-the-fly motion-compensated cone-beam ct using an a priori model of the respiratory motion med phys dynamic & 4d ct doi.org 1.3115691" }, { "id": "schlomka-2008", "title": "Experimental Feasibility of Multi-Energy Photon-Counting K-Edge Imaging in Pre-Clinical Computed Tomography", "year": 2008, "venue": "PMB", "preprint": false, "topics": [ "spectral" ], "links": { "paper": "https://doi.org/10.1088/0031-9155/53/15/002" }, "_q": "experimental feasibility of multi-energy photon-counting k-edge imaging in pre-clinical computed tomography pmb spectral & dual-energy ct doi.org 002" }, { "id": "leng-2008", "title": "High Temporal Resolution and Streak-Free Four-Dimensional Cone-Beam Computed Tomography", "year": 2008, "venue": "PMB", "preprint": false, "topics": [ "dynamic", "cbct" ], "links": { "paper": "https://doi.org/10.1088/0031-9155/53/20/006" }, "_q": "high temporal resolution and streak-free four-dimensional cone-beam computed tomography pmb dynamic & 4d ct cone-beam ct doi.org 006" }, { "id": "piccs", "title": "Prior Image Constrained Compressed Sensing (PICCS): A Method to Accurately Reconstruct Dynamic CT Images from Highly Undersampled Projection Data Sets", "year": 2008, "venue": "Med Phys", "preprint": false, "topics": [ "dynamic" ], "links": { "paper": "https://doi.org/10.1118/1.2836423" }, "abbr": "PICCS", "_q": "prior image constrained compressed sensing (piccs): a method to accurately reconstruct dynamic ct images from highly undersampled projection data sets piccs med phys dynamic & 4d ct doi.org 1.2836423" }, { "id": "roessl-2007", "title": "K-Edge Imaging in X-Ray Computed Tomography Using Multi-Bin Photon Counting Detectors", "year": 2007, "venue": "PMB", "preprint": false, "topics": [ "spectral" ], "links": { "paper": "https://doi.org/10.1088/0031-9155/52/15/020" }, "_q": "k-edge imaging in x-ray computed tomography using multi-bin photon counting detectors pmb spectral & dual-energy ct doi.org 020" }, { "id": "zbijewski-2006", "title": "Efficient Monte Carlo Based Scatter Artifact Reduction in Cone-Beam Micro-CT", "year": 2006, "venue": "TMI", "preprint": false, "topics": [ "scatter" ], "links": { "paper": "https://doi.org/10.1109/tmi.2006.872328" }, "_q": "efficient monte carlo based scatter artifact reduction in cone-beam micro-ct tmi scatter correction doi.org tmi.2006.872328" }, { "id": "zhu-2006", "title": "Scatter Correction Method for X-Ray CT Using Primary Modulation: Theory and Preliminary Results", "year": 2006, "venue": "TMI", "preprint": false, "topics": [ "scatter" ], "links": { "paper": "https://doi.org/10.1109/tmi.2006.884636" }, "_q": "scatter correction method for x-ray ct using primary modulation: theory and preliminary results tmi scatter correction doi.org tmi.2006.884636" }, { "id": "sonke-2005", "title": "Respiratory Correlated Cone Beam CT", "year": 2005, "venue": "Med Phys", "preprint": false, "topics": [ "dynamic", "cbct" ], "links": { "paper": "https://doi.org/10.1118/1.1869074" }, "_q": "respiratory correlated cone beam ct med phys dynamic & 4d ct cone-beam ct doi.org 1.1869074" }, { "id": "elbakri-2002", "title": "Statistical Image Reconstruction for Polyenergetic X-Ray Computed Tomography", "year": 2002, "venue": "TMI", "preprint": false, "topics": [ "spectral" ], "links": { "paper": "https://doi.org/10.1109/42.993128" }, "_q": "statistical image reconstruction for polyenergetic x-ray computed tomography tmi spectral & dual-energy ct doi.org 42.993128" }, { "id": "deman-2001", "title": "An Iterative Maximum-Likelihood Polychromatic Algorithm for CT", "year": 2001, "venue": "TMI", "preprint": false, "topics": [ "spectral" ], "links": { "paper": "https://doi.org/10.1109/42.959297" }, "_q": "an iterative maximum-likelihood polychromatic algorithm for ct tmi spectral & dual-energy ct doi.org 42.959297" }, { "id": "siewerdsen-2001", "title": "Cone-Beam Computed Tomography with a Flat-Panel Imager: Magnitude and Effects of X-Ray Scatter", "year": 2001, "venue": "Med Phys", "preprint": false, "topics": [ "scatter", "cbct" ], "links": { "paper": "https://doi.org/10.1118/1.1339879" }, "_q": "cone-beam computed tomography with a flat-panel imager: magnitude and effects of x-ray scatter med phys scatter correction cone-beam ct doi.org 1.1339879" }, { "id": "alvarez-1976", "title": "Energy-Selective Reconstructions in X-Ray Computerised Tomography", "year": 1976, "venue": "PMB", "preprint": false, "topics": [ "spectral" ], "links": { "paper": "https://doi.org/10.1088/0031-9155/21/5/002" }, "_q": "energy-selective reconstructions in x-ray computerised tomography pmb spectral & dual-energy ct doi.org 002" } ], "toolkits": [ { "name": "TIGRE", "url": "https://github.com/CERN/TIGRE", "language": "MATLAB / Python", "license": "BSD-3-Clause", "stars": 812, "tags": [ "CBCT", "micro-CT", "GPU", "iterative", "FDK" ], "note": "GPU-accelerated (CUDA) toolbox for cone-beam and parallel-beam CT; FDK, SART, SIRT, CGLS and TV variants." }, { "name": "ASTRA Toolbox", "url": "https://github.com/astra-toolbox/astra-toolbox", "language": "C++ / Python / MATLAB", "license": "GPL-3.0", "stars": 637, "tags": [ "parallel-beam", "fan-beam", "cone-beam", "GPU", "iterative" ], "note": "Long-standing research toolbox with a large set of projectors and algorithms; the reference CPU/GPU baseline.", "homepage": "https://astra-toolbox.com/" }, { "name": "tomosipo", "url": "https://github.com/cicwi/tomosipo", "language": "Python", "license": "GPL-3.0", "stars": 107, "tags": [ "geometry", "cone-beam", "differentiable", "PyTorch" ], "note": "Painless specification of 2D/3D projection geometries; wraps ASTRA and integrates with PyTorch." }, { "name": "ODL", "url": "https://github.com/odlgroup/odl", "language": "Python", "license": "MPL-2.0", "stars": 434, "tags": [ "operator-discretisation", "variational", "iterative" ], "note": "Operator Discretization Library — a functional-analytic framework for inverse problems, with CT geometries built in.", "homepage": "https://odlgroup.github.io/odl/" }, { "name": "Core Imaging Library (CIL)", "url": "https://github.com/TomographicImaging/CIL", "language": "Python", "license": "Apache-2.0", "stars": 155, "tags": [ "variational", "regularisation", "optimisation" ], "note": "CCPi framework for variational CT reconstruction with a large catalogue of optimisation algorithms.", "homepage": "https://www.ccpi.ac.uk/cil" }, { "name": "CCPi Regularisation Toolkit", "url": "https://github.com/TomographicImaging/CCPi-Regularisation-Toolkit", "language": "C / Python", "license": "Apache-2.0", "stars": 63, "tags": [ "TV", "TGV", "regularisation", "GPU" ], "note": "CPU/GPU implementations of TV, TGV, directional TV and other regularisers used by CIL." }, { "name": "LEAP", "url": "https://github.com/llnl/LEAP", "language": "CUDA / Python", "license": "MIT", "stars": 254, "tags": [ "CBCT", "MBIR", "GPU", "high-performance" ], "note": "LLNL's Livermore Energy-Aware Processor for 3D transmission CT; production-grade model-based reconstruction." }, { "name": "svmbir", "url": "https://github.com/cabouman/svmbir", "language": "C / Python", "license": "BSD-3-Clause", "stars": 28, "tags": [ "MBIR", "parallel-beam", "fan-beam", "proximal" ], "note": "Fast Super-Voxel Model Based Iterative Reconstruction with proximal-map plug-ins." }, { "name": "RTK", "url": "https://github.com/RTKConsortium/RTK", "language": "C++", "license": "Apache-2.0", "stars": 298, "tags": [ "CBCT", "ITK", "filtering", "FDK" ], "note": "Reconstruction Toolkit built on ITK; widely used in clinical CBCT and interventional research.", "homepage": "https://www.openrtk.org/" }, { "name": "PyTomography", "url": "https://github.com/PyTomography/PyTomography", "language": "Python", "license": "MIT", "stars": 173, "tags": [ "SPECT", "PET", "CT", "quantification" ], "note": "End-to-end medical image reconstruction with quantification, including CT-based attenuation correction." }, { "name": "OMEGA", "url": "https://github.com/villekf/OMEGA", "language": "MATLAB / Python", "license": "GPL-3.0", "stars": 111, "tags": [ "PET", "SPECT", "CT", "iterative" ], "note": "Open-source multi-dimensional tomographic reconstruction software covering PET/SPECT/CT." }, { "name": "TomoPy", "url": "https://github.com/tomopy/tomopy", "language": "Python", "license": "BSD-3-Clause", "stars": 397, "tags": [ "synchrotron", "gridrec", "phase-contrast" ], "note": "Reference toolkit for synchrotron micro/nano tomography; gridrec, FBP and phase retrieval." }, { "name": "RadIO", "url": "https://github.com/analysiscenter/radio", "language": "Python", "license": "Apache-2.0", "stars": 227, "tags": [ "radon", "filtered-backprojection", "teaching" ], "note": "Radon transforms and FBP in a compact, readable Python package." }, { "name": "pySART", "url": "https://github.com/djvine/pySART", "language": "Python", "license": "GPL-2.0", "stars": 33, "tags": [ "SART", "iterative", "teaching" ], "note": "Compact reference implementation of the Simultaneous Algebraic Reconstruction Technique." }, { "name": "libcbct", "url": "https://github.com/tatsy/libcbct", "language": "C++", "license": "See repository", "stars": 10, "tags": [ "CBCT", "FDK", "iterative" ], "note": "Lightweight cone-beam CT reconstruction library with FDK and iterative solvers." }, { "name": "tofu", "url": "https://github.com/ufo-kit/tofu", "language": "Python", "license": "LGPL-3.0", "stars": 20, "tags": [ "GPU", "filtering", "pipeline" ], "note": "Helper layer on top of the UFO framework for fast GPU tomographic reconstruction pipelines." }, { "name": "sigpy", "url": "https://github.com/mikgroup/sigpy", "language": "Python", "license": "BSD-3-Clause", "stars": 339, "tags": [ "iterative", "proximal", "GPU", "MRI" ], "note": "Signal-processing package for iterative image reconstruction; proximal operators and NUFFT/radon primitives." }, { "name": "DeepInverse", "url": "https://github.com/deepinv/deepinv", "language": "Python", "license": "BSD-3-Clause", "stars": 827, "tags": [ "PyTorch", "plug-and-play", "unrolling", "benchmark" ], "note": "PyTorch library for imaging inverse problems — physics operators, learned denoisers, unrolled networks and benchmarks.", "homepage": "https://deepinv.github.io/" }, { "name": "torch-radon", "url": "https://github.com/matteo-ronchetti/torch-radon", "language": "Python", "license": "GPL-3.0", "stars": 280, "tags": [ "differentiable", "PyTorch", "radon" ], "note": "Differentiable Radon transform and filtered backprojection in PyTorch." }, { "name": "LION", "url": "https://github.com/CambridgeCIA/LION", "language": "Python", "license": "GPL-3.0", "stars": 63, "tags": [ "learned-iterative", "unrolling", "PET", "CT" ], "note": "Learned Iterative Optimization Networks — unrolled reconstruction with PyTorch, used in CT and PET." }, { "name": "TomoPhantom", "url": "https://github.com/dkazanc/TomoPhantom", "language": "Python", "license": "Apache-2.0", "stars": 135, "tags": [ "phantom", "simulation", "2D", "3D", "4D" ], "note": "Analytical 2D/3D/4D phantom generation plus forward projection for controlled reconstruction experiments." }, { "name": "xraylib", "url": "https://github.com/tschoonj/xraylib", "language": "C / Python", "license": "See repository", "stars": 173, "tags": [ "physics", "cross-sections", "spectroscopy" ], "note": "X-ray matter interaction cross sections, fluorescence yields and Compton profiles; the physics layer for realistic simulation.", "homepage": "https://github.com/tschoonj/xraylib/wiki" }, { "name": "pydicom", "url": "https://github.com/pydicom/pydicom", "language": "Python", "license": "MIT", "stars": 2219, "tags": [ "DICOM", "I/O" ], "note": "Read, modify and write DICOM files — the standard entry point for clinical CT data.", "homepage": "https://pydicom.github.io/" }, { "name": "MONAI", "url": "https://github.com/Project-MONAI/MONAI", "language": "Python", "license": "Apache-2.0", "stars": 8760, "tags": [ "PyTorch", "medical-imaging", "deep-learning" ], "note": "PyTorch-based framework for medical imaging with CT reconstruction transforms and pretrained models.", "homepage": "https://monai.dev/" }, { "name": "tomviz", "url": "https://github.com/OpenChemistry/tomviz", "language": "C++", "license": "BSD-3-Clause", "stars": 367, "tags": [ "visualisation", "tomography" ], "note": "Cross-platform application for tomographic data visualisation and processing.", "homepage": "https://tomviz.org/" }, { "name": "MIRT", "url": "https://github.com/JeffFessler/MIRT.jl", "language": "Julia", "license": "MIT", "stars": 126, "tags": [ "statistical", "MBIR", "regularisation", "teaching" ], "note": "Michigan Image Reconstruction Toolbox. Reference implementations of a very wide range of classical, statistical and penalised-likelihood reconstruction methods; the Julia port of the long-standing MATLAB MIRT." }, { "name": "IRtools", "url": "https://github.com/jnagy1/IRtools", "language": "MATLAB", "license": "See repository", "stars": 91, "tags": [ "regularisation", "Krylov", "hybrid-methods", "teaching" ], "note": "Iterative Regularization Tools — hybrid Krylov methods, Tikhonov, TV and general-form regularisation, shipped with large-scale tomography test problems. From Hansen's group." }, { "name": "leehoy/CTReconstruction", "url": "https://github.com/leehoy/CTReconstruction", "language": "Python", "license": "GPL-2.0", "stars": 96, "tags": [ "FBP", "iterative", "teaching" ], "note": "Compact, readable Python implementations of FBP and iterative CT reconstruction algorithms — useful as a from-scratch reference." }, { "name": "Algotom", "url": "https://github.com/algotom/algotom", "language": "Python", "license": "Apache-2.0", "stars": 69, "tags": [ "synchrotron", "artefact-removal", "ring-artifact", "denoising" ], "note": "Data-processing algorithms for tomography — ring and artefact removal, distortion correction, denoising, phase retrieval and reconstruction. Developed for synchrotron beamlines." }, { "name": "Sarepy", "url": "https://github.com/nghia-vo/sarepy", "language": "Python", "license": "See repository", "stars": 63, "tags": [ "ring-artifact", "post-processing" ], "note": "Numerical techniques for ring-artefact removal in tomography — the most complete open collection of stripe/ring filters." }, { "name": "DBT-Reconstruction", "url": "https://github.com/LAVI-USP/DBT-Reconstruction", "language": "MATLAB", "license": "GPL-3.0", "stars": 62, "tags": [ "breast-tomosynthesis", "FBP", "iterative", "geometry" ], "note": "Open-source reconstruction toolbox for digital breast tomosynthesis, covering DBT-specific geometry alongside FBP and iterative solvers." }, { "name": "Discorpy", "url": "https://github.com/DiamondLightSource/discorpy", "language": "Python", "license": "Apache-2.0", "stars": 93, "tags": [ "geometry", "calibration", "distortion" ], "note": "Sub-pixel camera and lens distortion calibration; used to correct detector/geometry distortions before reconstruction." }, { "name": "Learned Primal-Dual", "url": "https://github.com/adler-j/learned_primal_dual", "language": "Python", "license": "See repository", "stars": 110, "tags": [ "unrolling", "primal-dual", "reference" ], "note": "Reference implementation of Learned Primal-Dual reconstruction — the canonical unrolled primal-dual scheme, originally applied to CT." }, { "name": "Learned Gradient Tomography", "url": "https://github.com/adler-j/learned_gradient_tomography", "language": "Python", "license": "See repository", "stars": 97, "tags": [ "unrolling", "learned-gradient", "reference" ], "note": "Reference implementation of learned gradient descent for ill-posed tomography (Adler & Öktem); the origin of many later unrolled CT networks." }, { "name": "Physics-ArX", "url": "https://github.com/nadeemlab/Physics-ArX", "language": "Python", "license": "See repository", "stars": 79, "tags": [ "augmentation", "noise-model", "artefact-model", "radiotherapy" ], "note": "Physics-based data-augmentation library that injects realistic CT/CBCT noise, scatter and artefact models into existing images to build paired training data." }, { "name": "LD-CT simulator", "url": "https://github.com/smuzd/LD-CT-simulation", "language": "MATLAB", "license": "See repository", "stars": 59, "tags": [ "low-dose", "simulation", "noise" ], "note": "Low-dose CT simulator that converts high-dose images into realistic low-dose counterparts using a validated noise model." }, { "name": "CBCT Scatter Correction Tool", "url": "https://github.com/YangkangJiang/Cone-beam-CT-scatter-correction-tool", "language": "Python", "license": "See repository", "stars": 15, "tags": [ "scatter", "cbct", "correction" ], "note": "One of the very few open implementations of cone-beam CT scatter estimation and correction." }, { "name": "3D Slicer", "url": "https://github.com/Slicer/Slicer", "language": "C++", "license": "BSD-style (see repository)", "stars": 2652, "tags": [ "platform", "visualisation", "DICOM", "segmentation" ], "note": "The dominant open platform for medical image computing; used to inspect, segment and register CT volumes and to prototype reconstruction pipelines as extensions.", "homepage": "https://www.slicer.org/" }, { "name": "voxenra", "url": "https://github.com/l5769389/voxenra", "language": "Python", "license": "See repository", "stars": 299, "tags": [ "viewer", "DICOM", "visualisation" ], "note": "Cross-platform DICOM viewer for CT, MRI and PET/CT with multiplanar reformatting, 3D volume rendering and fusion — handy for eyeballing reconstruction output." }, { "name": "PyLops", "url": "https://github.com/equinor/pylops", "language": "Python", "license": "LGPL-3.0", "stars": 540, "tags": [ "operator", "solver", "radon", "PyTorch", "JAX" ], "note": "Linear-operator library with a Radon transform and a large set of solvers (CGLS, LSQR, TV, sparsity-promoting). The cleanest way to prototype a variational CT problem without writing your own matrix-free operators.", "homepage": "https://pylops.readthedocs.io/" }, { "name": "mumott", "url": "https://gitlab.com/liebi-group/software/mumott", "language": "Python", "license": "GPL-3.0", "stars": 4, "tags": [ "tensor-tomography", "diffraction", "reconstruction" ], "note": "Tensor-tomography reconstruction for reciprocal-space data, developed at DTU. Specialised rather than general-purpose, but it is the most complete open implementation of the tensor-tomography model.", "homepage": "https://mumott.org/" }, { "name": "XrayPhysics", "url": "https://github.com/kylechampley/XrayPhysics", "language": "C++ / Python", "license": "MIT", "stars": 56, "tags": [ "physics", "spectra", "cross-sections", "dual-energy", "beam-hardening" ], "note": "X-ray cross sections, source-spectrum modelling, multi-material beam-hardening correction and dual-energy decomposition. From the LEAP author, and it pairs naturally with a simulator when you need a physically honest spectrum.", "homepage": "https://xrayphysics.readthedocs.io/" }, { "name": "pyHST2", "url": "https://gitlab.esrf.fr/tomotools/pyhst2", "language": "C / Python", "license": "See repository", "tags": [ "synchrotron", "phase-contrast", "reconstruction" ], "note": "The ESRF beamline reconstruction code — gridrec, FBP and iterative methods with phase retrieval for propagation-based phase-contrast tomography. Long-standing workhorse of the synchrotron community.", "homepage": "http://ftp.esrf.fr/scisoft/PYHST2/" } ], "datasets": [ { "name": "LoDoPaB-CT", "url": "https://zenodo.org/records/3384092", "modality": "2D fan-beam", "tasks": [ "low-dose", "sparse-view", "denoising", "reconstruction" ], "license": "CC BY 4.0", "note": "**Projection + image.** 41,000 simulated human thorax slices (LIDC/IDRI), two dose levels. The de-facto standard low-dose CT benchmark; ships a well-tuned FBP/U-Net reference pipeline.", "homepage": "https://lodopab.grand-challenge.org/" }, { "name": "LDCT-and-Projection-data", "url": "https://www.cancerimagingarchive.net/collection/ldct-and-projection-data/", "modality": "helical CT", "tasks": [ "low-dose", "reconstruction", "denoising" ], "license": "CC BY-NC 4.0", "note": "**Projection + image.** Mayo Clinic, released through TCIA. 299 thoracic / abdominal / head exams at four dose levels (full / quarter / 10% / 5%), with raw sinograms in the open **DICOM-CT-PD** format. It grew out of the 2016 AAPM Low Dose CT Grand Challenge and is now the best real-data source for projection-domain methods." }, { "name": "2DeteCT", "url": "https://zenodo.org/records/6984866", "modality": "2D fan-beam", "tasks": [ "reconstruction", "limited-angle", "sparse-view", "denoising" ], "license": "CC BY 4.0", "note": "**Projection + image.** 5,000 real experimental 2D slices of mixed objects, 3 dose levels, multiple source-detector geometries. Excellent for reproducible real-data CT benchmarking." }, { "name": "Walnut-CBCT", "url": "https://www.fips.fi/dataset.php", "modality": "cone-beam", "tasks": [ "reconstruction", "geometry" ], "license": "CC BY 4.0", "note": "**Projection only.** Finnish Inverse Problems Society. Real cone-beam projections of a walnut at several angular samplings — a standard test bed for sparse-view and limited-angle CBCT." }, { "name": "Helsinki Tomography Challenge 2022", "url": "https://www.fips.fi/HTC2022.php", "modality": "2D fan-beam", "tasks": [ "limited-angle", "reconstruction" ], "license": "CC BY 4.0", "note": "**Projection only.** Real limited-angle sinograms of phantoms and of a lotus root; the accompanying challenge defines the standard limited-angle protocol." }, { "name": "SPARE 4D-CBCT", "url": "https://image-x.sydney.edu.au/spare-challenge/", "modality": "cone-beam, 4D", "tasks": [ "dynamic", "cbct", "reconstruction" ], "license": "research use", "note": "**Projection + image.** Thoracic 4D cone-beam CT for breathing-motion-resolved reconstruction; the reference benchmark for dynamic CBCT." }, { "name": "ToothFairy2", "url": "https://doi.org/10.5281/zenodo.10990960", "modality": "cone-beam, dental", "tasks": [ "cbct", "reconstruction", "segmentation" ], "license": "CC BY 4.0", "note": "480 dental CBCT scans with 3D tooth and jaw annotations; large-scale and useful for CBCT-domain pretraining. **Image domain only** — volumes are released without raw projections.", "homepage": "https://toothfairy2.grand-challenge.org/" }, { "name": "Cone-Beam CT (CBCT) Head & Neck", "url": "https://www.cancerimagingarchive.net/collection/head-neck/", "modality": "cone-beam", "tasks": [ "cbct", "reconstruction" ], "license": "CC BY-NC 3.0", "note": "Paired planning CT and on-board CBCT — the standard setting for CBCT correction and synthetic-CT work in radiotherapy." }, { "name": "LIDC-IDRI", "url": "https://www.cancerimagingarchive.net/collection/lidc-idri/", "modality": "helical CT", "tasks": [ "denoising", "segmentation", "low-dose" ], "license": "CC BY 3.0", "note": "1,018 thoracic CT scans with four-radiologist nodule annotations. The source anatomy behind LoDoPaB-CT and most simulated low-dose data." }, { "name": "DeepLesion", "url": "https://nihcc.app.box.com/v/DeepLesion", "modality": "helical CT", "tasks": [ "detection", "denoising" ], "license": "CC BY 3.0", "note": "32,735 lesion annotations across 10,594 studies from 4,427 patients — a large-scale pretraining corpus for CT-domain backbones." }, { "name": "LUNA16", "url": "https://luna16.grand-challenge.org/", "modality": "helical CT", "tasks": [ "detection", "denoising" ], "license": "CC BY 3.0", "note": "888 thin-slice chest CT scans with unified 1 mm resampling and nodule annotations; a clean, well-curated denoising/detection benchmark." }, { "name": "KiTS23", "url": "https://kits-challenge.org/kits23/", "modality": "contrast CT", "tasks": [ "segmentation", "reconstruction" ], "license": "CC BY-NC 4.0", "note": "489 abdominal CT scans with kidney-tumour and cyst annotations across three challenge editions." }, { "name": "Pancreas-CT (NIH)", "url": "https://www.cancerimagingarchive.net/collection/pancreas-ct/", "modality": "contrast CT", "tasks": [ "segmentation" ], "license": "CC BY 3.0", "note": "82 abdominal contrast CT scans with expert pancreas masks; a small but very widely used reference set." }, { "name": "BTCV (Beyond the Cranial Vault)", "url": "https://www.synapse.org/#!Synapse:syn3193805/wiki/217789", "modality": "contrast CT", "tasks": [ "segmentation" ], "license": "CC BY-NC 4.0", "note": "30 abdominal CT scans with 13-organ annotations; the origin of the FLARE/AMOS lineage of multi-organ benchmarks." }, { "name": "TotalSegmentator", "url": "https://zenodo.org/records/10047292", "modality": "contrast CT", "tasks": [ "segmentation", "reconstruction" ], "license": "CC BY 4.0", "note": "1,228 CT scans with 104 anatomical structures — the largest open CT structure set, and a strong pretraining target." }, { "name": "AMOS22", "url": "https://amos22.grand-challenge.org/", "modality": "CT / MRI", "tasks": [ "segmentation" ], "license": "CC BY-NC-SA 4.0", "note": "500 CT + 100 MRI abdominal scans, 15 organs; deliberately heterogeneous scanners, so it stresses robustness." }, { "name": "Medical Segmentation Decathlon", "url": "http://medicaldecathlon.com/", "modality": "CT / MRI", "tasks": [ "segmentation", "reconstruction" ], "license": "CC BY-SA 4.0", "note": "Ten tasks, four of them CT (lung, pancreas, colon, hepatic vessels). The single most cited multi-task medical segmentation benchmark." }, { "name": "VerSe", "url": "https://github.com/anjany/verse", "modality": "CT / CBCT", "tasks": [ "segmentation", "cbct" ], "license": "CC BY-SA 4.0", "note": "3,741 CT/CBCT spine scans with vertebra and disc labels; mixes clinical CT with CBCT, which makes it relevant for artefact robustness." }, { "name": "RibFrac", "url": "https://ribfrac.grand-challenge.org/", "modality": "CT", "tasks": [ "detection", "segmentation" ], "license": "CC BY-NC 4.0", "note": "5,000 CT scans with 660 rib-fracture annotations; large, and often used as an auxiliary CT corpus." }, { "name": "CT-ORG", "url": "https://www.cancerimagingarchive.net/collection/ct-org/", "modality": "contrast CT", "tasks": [ "segmentation" ], "license": "CC BY 3.0", "note": "140 CT scans with multi-organ masks, including a subset of the Liver Tumor Segmentation benchmark." }, { "name": "STOIC 2021", "url": "https://portal.imaging.datacommons.cancer.gov/collections/stoic/", "modality": "CT", "tasks": [ "diagnosis", "low-dose" ], "license": "CC BY-NC 3.0", "note": "23,000+ COVID-19 chest CT scans from a multi-centre international study; a very large real-clinical distribution shift test. Listed here through the NCI Imaging Data Commons mirror, which exposes the same collection with a queryable API." }, { "name": "MosMedData", "url": "https://mosmed.ai/en/datasets/datasets/covid191110/", "modality": "CT", "tasks": [ "diagnosis", "low-dose" ], "license": "CC BY-NC-ND 3.0", "note": "1,110 chest CT scans with COVID-19 severity grades; frequently reused as a low-quality / low-dose robustness set." }, { "name": "HNSCC (Head & Neck)", "url": "https://www.cancerimagingarchive.net/collection/hnscc/", "modality": "contrast CT + PET", "tasks": [ "segmentation", "reconstruction" ], "license": "CC BY-NC 3.0", "note": "Multi-institution head-and-neck CT with GTV/CTV delineations; pairs with the HECKTOR challenge." }, { "name": "CTPelvic1K", "url": "https://github.com/MIRACLE-Center/CTPelvic1K", "modality": "contrast CT", "tasks": [ "segmentation", "metal-artifact" ], "license": "CC BY-NC 4.0", "note": "1,184 pelvic CT scans across 7 sub-datasets; notably includes **metal-implant** cases, one of the few open sources of real metal artefacts." }, { "name": "FLARE22", "url": "https://flare22.grand-challenge.org/", "modality": "contrast CT", "tasks": [ "segmentation" ], "license": "CC BY-NC-SA 4.0", "note": "2,000 abdominal CT scans with 13-organ labels across 20+ scanners; a large-scale robustness benchmark." }, { "name": "AutoPET-II", "url": "https://autopet-ii.grand-challenge.org/", "modality": "PET/CT", "tasks": [ "segmentation", "reconstruction" ], "license": "CC BY-NC 4.0", "note": "1,014 whole-body PET/CT studies with lesion masks; relevant when CT reconstruction feeds a downstream task." }, { "name": "HECKTOR", "url": "https://hecktor.grand-challenge.org/", "modality": "PET/CT", "tasks": [ "segmentation", "prognosis" ], "license": "CC BY-NC 4.0", "note": "Head-and-neck PET/CT with primary-tumour delineations; five editions of consistent annotations." }, { "name": "CT Lymph Nodes", "url": "https://www.cancerimagingarchive.net/collection/ct-lymph-nodes/", "modality": "contrast CT", "tasks": [ "detection", "segmentation" ], "license": "CC BY 3.0", "note": "176 abdominal CT scans with mediastinal and abdominal lymph-node annotations." }, { "name": "NLST", "url": "https://www.cancerimagingarchive.net/collection/nlst/", "modality": "low-dose CT", "tasks": [ "denoising", "detection" ], "license": "restricted (TCIA NCI)", "note": "26,254 baseline low-dose screening CT scans — by far the largest real low-dose CT collection, though access is gated." }, { "name": "AAPM DL-Sparse-View CT data", "url": "https://www.aapm.org/GrandChallenge/DL-sparse-view-CT/", "modality": "helical CT (re-projected)", "tasks": [ "sparse-view", "reconstruction" ], "license": "CC BY 3.0", "note": "**Projection + image.** The 2016 challenge cohort re-projected to 2/4/8/16/32/64 views per rotation, giving a controlled sparse-view axis with a fixed anatomical ground truth." }, { "name": "Finnish Inverse Problems Society (FIPS) datasets", "url": "https://www.fips.fi/dataset.php", "modality": "fan-beam / cone-beam", "tasks": [ "reconstruction", "geometry", "calibration" ], "license": "CC BY 4.0", "note": "**Projection only.** A family of real measured sinograms (walnut, lotus root, apple, carrot, phantoms) with carefully documented acquisition geometry — the cleanest public source for testing reconstruction operators." }, { "name": "LoDoPaB-CT (benchmark release paper)", "url": "https://doi.org/10.1038/s41597-021-00893-z", "modality": "2D fan-beam", "tasks": [ "low-dose", "reconstruction", "benchmarking" ], "license": "CC BY 4.0", "note": "The **Scientific Data** descriptor for the LoDoPaB-CT dataset — the citation to use when you report results on this split. Documents the simulation protocol and the FBP/U-Net reference baseline.", "homepage": "https://lodopab.grand-challenge.org/" }, { "name": "COBRA2026: a large-scale multicenter pelvic cone-beam computed tomography projection dataset", "url": "https://arxiv.org/abs/2607.20037", "tasks": [ "reconstruction", "benchmarking" ], "note": "Released as a public projection dataset (see the paper for access). ", "year": 2026 }, { "name": "MORE: Multi-Organ Medical Image REconstruction Dataset", "url": "https://arxiv.org/abs/2510.26759", "tasks": [ "reconstruction", "benchmarking" ], "note": "Released as a public projection dataset (see the paper for access). Accepted to ACMMM 2025", "year": 2025 } ], "benchmarks": [ { "name": "AAPM Low-Dose CT Grand Challenge", "url": "https://www.aapm.org/grandchallenge/lowdosect/", "year": 2016, "tasks": [ "low-dose", "denoising", "reconstruction" ], "note": "The challenge that established the quarter-dose / 10% / 5% protocol and the Mayo abdominal cohort. Nearly every low-dose CT paper still reports on this split." }, { "name": "AAPM DL-Sparse-View CT Challenge", "url": "https://www.aapm.org/GrandChallenge/DL-sparse-view-CT/", "year": 2022, "tasks": [ "sparse-view", "reconstruction" ], "note": "Fixed sparse-view protocols (2/4/8/16/32/64 views) on re-projected clinical data, with official metrics and a public leaderboard. The standard reference point for sparse-view CT." }, { "name": "Helsinki Tomography Challenge", "url": "https://www.fips.fi/HTC2022.php", "year": 2022, "tasks": [ "limited-angle", "reconstruction" ], "note": "Real measured limited-angle sinograms. Notable because the winning entries were classical / model-based rather than purely learned — a useful counterweight." }, { "name": "LoDoPaB-CT benchmark", "url": "https://lodopab.grand-challenge.org/", "year": 2021, "tasks": [ "low-dose", "reconstruction" ], "note": "Grand-challenge style evaluation on the LoDoPaB-CT split, with a published, tuned FBP+U-Net reference baseline so improvements are measurable." }, { "name": "SPARE Challenge", "url": "https://image-x.sydney.edu.au/spare-challenge/", "year": 2024, "tasks": [ "dynamic", "cbct", "reconstruction" ], "note": "Thoracic 4D cone-beam CT reconstruction from a one-minute scan. The first widely adopted benchmark for breathing-resolved dynamic CBCT; run by the Image X Institute at the University of Sydney." }, { "name": "MICCAI FLARE", "url": "https://flare.grand-challenge.org/", "year": 2021, "tasks": [ "segmentation" ], "note": "Multi-organ abdominal CT segmentation across four editions (FLARE21/22/23/24); the standard downstream-robustness target for CT reconstruction outputs." }, { "name": "Medical Segmentation Decathlon", "url": "http://medicaldecathlon.com/", "year": 2018, "tasks": [ "segmentation" ], "note": "Ten tasks with a fixed, hidden test set and a strict rule that no task-specific tuning is allowed — a genuinely fair generalisation benchmark." }, { "name": "KiTS Challenge", "url": "https://kits-challenge.org/", "year": 2019, "tasks": [ "segmentation" ], "note": "Kidney tumour segmentation, three editions (2019/2021/2023) with strictly controlled annotation quality and a strong emphasis on cross-institution generalisation." }, { "name": "VerSe Challenge", "url": "https://verse2019.grand-challenge.org/", "year": 2019, "tasks": [ "segmentation", "cbct" ], "note": "Vertebra labelling on both CT and CBCT, with a large hidden test set; the CBCT half makes it a natural stress test for artefact-heavy inputs." }, { "name": "CHAOS Challenge", "url": "https://chaos.grand-challenge.org/", "year": 2019, "tasks": [ "segmentation" ], "note": "Abdominal CT and MRI organ segmentation including low-dose and unenhanced protocols, with explicit cross-modality evaluation." }, { "name": "SPIE-AAPM-NCI LungX Challenge", "url": "https://www.cancerimagingarchive.net/collection/spie-aapm-lung-ct-challenge/", "year": 2015, "tasks": [ "detection", "low-dose" ], "note": "Lung nodule detection on low-dose screening CT; an early demonstration that reader-level performance on low-dose data is attainable. Data is distributed through TCIA." }, { "name": "AutoPET Challenge", "url": "https://autopet.grand-challenge.org/", "year": 2022, "tasks": [ "segmentation" ], "note": "Whole-body PET/CT lesion segmentation across three editions, with a deliberately hidden multi-centre test cohort." }, { "name": "HECKTOR Challenge", "url": "https://hecktor.grand-challenge.org/", "year": 2020, "tasks": [ "segmentation", "prognosis" ], "note": "Head-and-neck PET/CT tumour delineation; five editions make it one of the longer-running medical imaging challenges." }, { "name": "CTooth / CTooth+", "url": "https://github.com/liangjiubujiu/CTooth", "year": 2022, "tasks": [ "segmentation", "cbct" ], "note": "Fully annotated 3D dental CBCT dataset and benchmark for tooth segmentation (5,803 CBCT slices), later extended to CTooth+. A small but well-annotated CBCT benchmark in a domain where artefacts are severe." }, { "name": "Noise2Noise denoising protocol", "url": "https://github.com/NVlabs/noise2noise", "year": 2018, "tasks": [ "denoising", "self-supervised" ], "note": "The reference implementation that popularised training a denoiser without clean targets. On CT it became the standard 'no clean ground truth' evaluation protocol — most unsupervised CT denoising papers report on a Mayo-LDCT-style split under this setting." }, { "name": "SynthRAD2023 Challenge", "url": "https://synthrad2023.grand-challenge.org/", "year": 2023, "tasks": [ "cbct", "synthetic-ct", "reconstruction" ], "note": "Synthetic CT generation from CBCT and MRI. Relevant here because the CBCT-to-CT task is exactly where reconstruction artefacts (scatter, truncation, beam hardening) dominate — the challenge forces methods to handle them rather than assume clean input." }, { "name": "DeepInverse benchmark suite", "url": "https://deepinv.github.io/", "year": 2024, "tasks": [ "reconstruction", "benchmarking" ], "note": "A unified PyTorch benchmark harness covering CT, MRI, deblurring and inpainting, with reproducible metrics and pretrained baselines — the most practical way to compare a new CT method against strong generic solvers." }, { "name": "Generating synthetic computed tomography for radiotherapy: SynthRAD2025 challenge report", "url": "https://arxiv.org/abs/2605.13555", "year": 2026, "tasks": [ "reconstruction" ], "note": "59 pages total: 26 pages main article + supplementary material; 8 figures in the main manuscript and 3 supplementary figures. Currently under review at the journal Medical Image An" }, { "name": "CT-DegradBench: A Physics-Informed Benchmark for CT Degradation Detection and Severity Estimation", "url": "https://arxiv.org/abs/2605.16431", "year": 2026, "tasks": [ "reconstruction" ], "note": "Accepted in CVPR 2026 VISION Workshop (DEXTER track)" } ], "learning": [ { "name": "Principles of Computerized Tomographic Imaging", "url": "https://www.slaney.org/pct/pct-toc.html", "type": "book", "note": "Kak & Slaney (1988). **Free PDF.** The foundation: Radon transform, Fourier-slice theorem, FBP, algebraic reconstruction, fan/cone-beam rebinning. Read chapters 1-3 first." }, { "name": "The Mathematics of Computerized Tomography", "url": "https://doi.org/10.1137/1.9780898719284", "type": "book", "note": "Natterer (1986, SIAM reissue). The rigorous inverse-problem treatment — Radon transform on Sobolev spaces, sampling theory, ill-posedness and regularisation." }, { "name": "Computed Tomography - From Photon Statistics to Modern Cone-Beam CT", "url": "https://doi.org/10.1007/978-3-540-39408-2", "type": "book", "note": "Buzug (2008). The best single bridge from the physics (photon statistics, polychromaticity, detector response) to the reconstruction algorithms." }, { "name": "Fundamentals of Computerized Tomography - Image Reconstruction from Projections", "url": "https://doi.org/10.1007/978-1-84628-723-7", "type": "book", "note": "Herman (2nd ed. 2009). Very practical, with explicit algorithms, pseudocode and a careful treatment of sampling and discretisation artefacts." }, { "name": "Medical Image Reconstruction - A Conceptual Tutorial", "url": "https://doi.org/10.1007/978-3-642-05368-9", "type": "book", "note": "Zeng (2010). Deliberately intuition-first: explains *why* FBP, iterative and analytic methods behave the way they do, with minimal notation." }, { "name": "Foundations of Image Science", "url": "https://doi.org/10.1002/0471722138", "type": "book", "note": "Barrett & Myers (2004). The encyclopaedic reference for imaging-system theory — Fourier crosstalk, task-based assessment, and the mathematical basis of iterative reconstruction." }, { "name": "Computed Tomography - Principles, Design, Artifacts, and Recent Advances", "url": "https://www.spiedigitallibrary.org/ebooks/PM/Computed-Tomography-Principles-Design-Artifacts-and-Recent-Advances-Third-Edition/eISBN-9781628418040/10.1117/3.1764041", "type": "book", "note": "Hsieh (3rd ed. 2015, SPIE). Written from inside a CT vendor: system design, dose, artefact taxonomy and clinical correction strategies." }, { "name": "Principles of Medical Imaging (MIT OCW 22.058)", "url": "https://ocw.mit.edu/courses/22-058-principles-of-medical-imaging-fall-2002/", "type": "course", "note": "Free lecture notes and problem sets covering projection imaging, the Radon transform and reconstruction alongside MRI, ultrasound and PET." }, { "name": "ASTRA Toolbox documentation and tutorials", "url": "https://astra-toolbox.com/docs/index.html", "type": "tutorial", "note": "The most accessible hands-on entry point: CPU/GPU forward and back projectors, FBP, SART/SIRT, CGLS, with runnable examples for each geometry." }, { "name": "TIGRE demos", "url": "https://github.com/CERN/TIGRE/tree/master/Python/demos", "type": "tutorial", "note": "Runnable GPU demos from analytical FBP through iterative, total-variation and plug-and-play reconstruction, plus a CBCT geometry-calibration walkthrough." }, { "name": "ODL examples", "url": "https://github.com/odlgroup/odl/tree/master/examples", "type": "tutorial", "note": "Shows how to express a CT problem as operators and functionals, then solve it with proximal methods — the clearest introduction to variational CT." }, { "name": "Radon transform in scikit-image", "url": "https://scikit-image.org/docs/stable/auto_examples/transform/plot_radon_transform.html", "type": "tutorial", "note": "Twenty lines of code from a phantom to a sinogram and back with FBP; the fastest way to build intuition before touching a real geometry." }, { "name": "DeepInverse documentation", "url": "https://deepinv.github.io/", "type": "tutorial", "note": "Modern PyTorch-first tutorial track: physics operators, learned denoisers, plug-and-play and diffusion samplers, all with CT examples." }, { "name": "XDesign", "url": "https://github.com/AdvancedPhotonSource/xdesign", "type": "tool", "note": "Differentiable CT acquisition simulation — model polychromatic spectra, detector response and geometry inside a training loop. Originally developed alongside CIL; now maintained by the Advanced Photon Source." }, { "name": "SpekPy", "url": "https://pypi.org/project/spekpy/", "type": "tool", "note": "X-ray tube spectrum simulation (TASMIP/IPEM lineage), distributed as a Python package. Use it to generate realistic polychromatic spectra for beam-hardening experiments." }, { "name": "TomoPhantom", "url": "https://github.com/dkazanc/TomoPhantom", "type": "tool", "note": "Fast analytical 2D/3D/4D phantom generation with built-in noise and offset models; convenient for controlled reconstruction studies." }, { "name": "gVXR (gVirtualXray)", "url": "https://gvirtualxray.sourceforge.io/", "type": "tool", "note": "GPU-accelerated X-ray projection simulator supporting arbitrary 3D scenes and polychromatic spectra — useful for building large synthetic projection datasets." }, { "name": "SimpleITK", "url": "https://github.com/SimpleITK/SimpleITK", "type": "tool", "note": "The standard I/O and resampling layer for medical volumes; almost every CT dataset in this list is easiest to load through it." }, { "name": "Awesome CT Reconstruction (LoraLinH)", "url": "https://github.com/LoraLinH/Awesome-CT-Reconstruction", "type": "list", "note": "The best-known prior CT reconstruction list. Useful for cross-checking coverage of the 2020-2024 literature." }, { "name": "CT Denoising Review", "url": "https://github.com/SSinyu/CT-Denoising-Review", "type": "list", "note": "Dedicated to low-dose CT denoising, with an emphasis on the SSinyu/Mayo lineage of methods." }, { "name": "Awesome 3D Gaussian Splatting", "url": "https://github.com/MrNeRF/awesome-3D-gaussian-splatting", "type": "list", "note": "The reference 3DGS list. Its tomography-adjacent entries (r2_gaussian, X-Gaussian, X2-Gaussian) are the bridge to Gaussian-splatting CT." }, { "name": "Awesome NeRF and 3DGS for SLAM", "url": "https://github.com/3D-Vision-World/awesome-NeRF-and-3DGS-SLAM", "type": "list", "note": "Neural-field literature in the robotics/vision community; the source of the implicit-representation techniques now being adapted to CT." }, { "name": "Low-Dose CT Denoising (code collection)", "url": "https://github.com/houguanqun/Low-Dose-CT-denoising", "type": "list", "note": "A running collection of low-dose CT denoising code releases, organised by year — convenient for locating the implementation behind a given paper." }, { "name": "Awesome Medical Imaging", "url": "https://github.com/fepegar/awesome-medical-imaging", "type": "list", "note": "Broader medical image analysis resources: datasets, toolkits and pretrained models that are frequently reused in CT pipelines." }, { "name": "X-Ray Data Booklet", "url": "https://xdb.lbl.gov/", "type": "tool", "note": "**LBNL.** The standard quick reference for X-ray properties of the elements — absorption edges, fluorescence yields and scattering cross-sections. The first place to look when a simulation needs a physical constant." }, { "name": "NIST X-Ray Mass Attenuation Coefficients", "url": "https://www.nist.gov/pml/x-ray-mass-attenuation-coefficients", "type": "tool", "note": "**NIST.** Authoritative tabulation of mu/rho and mu_en/rho across the periodic table. What XrayPhysics and SpekPy are internally calibrated against — useful whenever you need to sanity-check a polychromatic model." }, { "name": "CT Principles and Algorithms", "url": "https://www.google.com/search?q=%E5%BA%84%E5%A4%A9%E6%88%88+CT%E5%8E%9F%E7%90%86%E4%B8%8E%E7%AE%97%E6%B3%95", "type": "book", "note": "庄天戈. The Chinese-language introduction to CT principles and algorithms; widely used as a first course text and the natural entry point for readers who prefer Chinese." }, { "name": "Industrial CT Technology and Principles", "url": "https://www.google.com/search?q=%E5%BC%A0%E6%9C%9D%E5%AE%97+%E5%B7%A5%E4%B8%9ACT%E6%8A%80%E6%9C%AF%E5%92%8C%E5%8E%9F%E7%90%86", "type": "book", "note": "张朝宗. The reference for industrial (non-destructive-testing) CT — geometry, sources, detectors and artefact sources on the industrial side, where the medical textbooks stop." }, { "name": "Medical Tomographic Image Reconstruction Simulation Experiments", "url": "https://www.google.com/search?q=%E9%BB%84%E5%8A%9B%E5%AE%87+%E5%8C%BB%E5%AD%A6%E6%96%AD%E5%B1%82%E5%9B%BE%E5%83%8F%E9%87%8D%E5%BB%BA%E4%BB%BF%E7%9C%9F%E5%AE%9E%E9%AA%8C", "type": "book", "note": "黄力宇. A hands-on Chinese-language lab manual: builds each reconstruction algorithm as a simulation experiment rather than presenting it as theory." } ] }