Score-Based Generative Models for PET Image Reconstruction

Abstract

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 $\text{in-silico}$ 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.

Accepted for publication at the Journal of Machine Learning for Biomedical Imaging (MELBA) https://melba-journal.org/2024:001

References in corpus (13)

• Diffusion Models Beat GANs on Image Synthesis
• Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding
• Score-Based Generative Modeling through Stochastic Differential Equations
• Classifier-Free Diffusion Guidance
• Diffusion-LM Improves Controllable Text Generation
• Tackling the Generative Learning Trilemma with Denoising Diffusion GANs
• Brain Imaging Generation with Latent Diffusion Models
• PET image denoising based on denoising diffusion probabilistic models
• Denoising Diffusion Models for Plug-and-Play Image Restoration
• Optimizing Sampling Patterns for Compressed Sensing MRI with Diffusion Generative Models
• Reflected Diffusion Models
• MRI Reconstruction with Side Information using Diffusion Models
• Learning Gradually Non-convex Image Priors Using Score Matching

Cited by in corpus (5)

• A Review on Low-Dose Emission Tomography Post-Reconstruction Denoising with Neural Network Approaches
• Artificial Intelligence-Guided PET Image Reconstruction and Multi-Tracer Imaging: Novel Methods, Challenges, And Opportunities
• Generative-Model-Based Fully 3D PET Image Reconstruction by Conditional Diffusion Sampling
• Multi-Subject Image Synthesis as a Generative Prior for Single-Subject PET Image Reconstruction
• Supervised Diffusion-Model-Based PET Image Reconstruction