mlsanityData to 7 Oct 2026

Score-Based Generative Models for PET Image Reconstruction

arXiv 2308.14190 ↗First posted 27 Aug 2023eess.IV cs.AI cs.CVcited by 22

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Score-based generative models have demonstrated highly promising results for medical image reconstruction tasks in magnetic resonance imaging or computed tomography. However, their application to Positron Emission Tomography (PET) is still largely unexplored. PET image reconstruction involves a variety of challenges, including Poisson noise with high variance and a wide dynamic range. To address these challenges, we propose several PET-specific adaptations of score-based generative models. The proposed framework is developed for both 2D and 3D PET. In addition, we provide an extension to guided reconstruction using magnetic resonance images. We validate the approach through extensive 2D and 3D textitin-silico experiments with a model trained on patient-realistic data without lesions, and evaluate on data without lesions as well as out-of-distribution data with lesions. This demonstrates the proposed method's robustness and significant potential for improved PET reconstruction.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 30 of its 77 references that are in the map. First posted on arXiv 27 Aug 2023.

Builds on

30 of 77 references.

Closest ancestors · 6

Same direction, newest first

  1. 2023MRI Reconstruction with Side Information using Diffusion Models26 Mar
  2. 2022Solving 3D Inverse Problems using Pre-trained 2D Diffusion Models19 Nov
  3. 2022Brain Imaging Generation with Latent Diffusion Models15 Sep
  4. 2022PET image denoising based on denoising diffusion probabilistic models13 Sep
  5. 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Models15 Nov
  6. 2021Score-based diffusion models for accelerated MRI8 Oct

Other references · 24

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2020Denoising Diffusion Implicit Modelscited by 9,655
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  7. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  8. 2022Classifier-Free Diffusion Guidancecited by 5,717
  9. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  10. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,375
  11. 2017Deep Image Priorcited by 1,097
  12. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,006
12 more
  1. 2021Maximum Likelihood Training of Score-Based Diffusion Modelscited by 670
  2. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANscited by 515
  3. 2016Deep Convolutional Neural Network for Inverse Problems in Imagingcited by 431
  4. 2023Denoising Diffusion Models for Plug-and-Play Image Restorationcited by 335
  5. 2021Robust Compressed Sensing MRI with Deep Generative Priorscited by 284
  6. 2017Learned Primal-dual Reconstructioncited by 251
  7. 2019On instabilities of deep learning in image reconstruction - Does AI come at a cost?cited by 211
  8. 2023Reflected Diffusion Modelscited by 81
  9. 2022Test-Time Training Can Close the Natural Distribution Shift Performance Gap in Deep Learning Based Compressed Sensingcited by 37
  10. 2020Denoising Score-Matching for Uncertainty Quantification in Inverse Problemscited by 11
  11. 2022List-Mode PET Image Reconstruction Using Deep Image Priorcited by 9
  12. 2023Learning Gradually Non-convex Image Priors Using Score Matchingcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 6; 2025: 9; 2026: 6.

22 papers.

Sort:

By area:

  1. 2023Steerable Conditional Diffusion for Out-of-Distribution Adaptation in Medical Image Reconstructioncited by 15
  2. 2024Likelihood-Scheduled Score-Based Generative Modeling for Fully 3D PET Image Reconstructioncited by 9
  3. 2025PET Image Reconstruction Using Deep Diffusion Image Priorcited by 6
  4. 2024Physics-Inspired Generative Models in Medical Imaging: A Reviewcited by 5
  5. 2025Efficient Bayesian Computation Using Plug-and-Play Priors for Poisson Inverse Problemscited by 2
  6. 2025Personalized MR-Informed Diffusion Models for 3D PET Image Reconstructioncited by 2
  7. 2024Mixed Noise and Posterior Estimation with Conditional DeepGEMcited by 1
  8. 2024Pseudo-MRI-Guided PET Image Reconstruction Method Based on a Diffusion Probabilistic Modelcited by 1
  9. 2024Generative-Model-Based Fully 3D PET Image Reconstruction by Conditional Diffusion Samplingcited by 1
  10. 2024Multi-Subject Image Synthesis as a Generative Prior for Single-Subject PET Image Reconstructioncited by 1
  11. 2025Supervised Diffusion-Model-Based PET Image Reconstructioncited by 1
  12. 2025TauGenNet: Plasma-Driven Tau PET Image Synthesis via Text-Guided 3D Diffusion Modelscited by 1
10 more
  1. 2025Steerable Conditional Diffusion for Domain Adaptation in PET Image Reconstructioncited by 1
  2. 2026PET-Adapter: Test-Time Domain Adaptation for Full and Limited-Angle PET Image Reconstructioncited by 1
  3. 2026A Stability Benchmark of Generative Regularizers for Inverse Problemscited by 1
  4. 2025Two-stage deep learning framework for the restoration of incomplete-ring PET imagescited by 0
  5. 2025Score-based Generative Diffusion Models to Synthesize Full-dose FDG Brain PET from MRI in Epilepsy Patientscited by 0
  6. 2025Bregman geometry-aware split Gibbs sampling for Bayesian Poisson inverse problemscited by 0
  7. 2026CT-Conditioned Diffusion Prior with Physics-Constrained Sampling for PET Super-Resolutioncited by 0
  8. 2026HDDPM: Heteroscedastic Denoising Diffusion Probabilistic Model for Quantitative Low-Count Brain PET Recoverycited by 0
  9. 2026Flow Matching-Based PET Image Reconstructioncited by 0
  10. 2026Manifold-Constrained PET Reconstruction with Learned Flow-Matching Priorscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Solving Inverse Problems with Score-Based Generative Priors learned from Noisy Data
  2. 2024LegoPET: Hierarchical Feature Guided Conditional Diffusion for PET Image Reconstruction
  3. 2025Pseudoinverse Diffusion Models for Generative CT Image Reconstruction from Low Dose Data
  4. 2025PET2Rep: Towards Vision-Language Model-Drived Automated Radiology Report Generation for Positron Emission Tomography
  5. 2023Data-iterative Optimization Score Model for Stable Ultra-Sparse-View CT Reconstruction
  6. 2024Convergence Properties of Score-Based Models for Linear Inverse Problems Using Graduated Optimisation
  7. 2024Dose-aware Diffusion Model for 3D PET Image Denoising: Multi-institutional Validation with Reader Study and Real Low-dose Data
  8. 2023Generative AI for Medical Imaging: extending the MONAI Framework