Bayesian PET Reconstruction with Learned Flow Matching Priors via Langevin Sampling

Abstract

Image reconstruction for positron emission tomography (PET) is a challenging inverse problem due to its inherent ill-posedness and Poisson counting noise, particularly in low-dose acquisitions. In this work, we introduce a novel Bayesian PET reconstruction framework that leverages a flow-matching generative prior learned from high-quality PET images. By incorporating this prior, we formulate PET reconstruction as a Bayesian inference problem and solve it via latent-space posterior sampling using the unadjusted Langevin algorithm. We evaluate the proposed method through numerical experiments and benchmark it against classical reconstruction methods and state-of-the-art deep learning-based baselines. The proposed method achieves improved reconstruction performance while enabling posterior uncertainty quantification.

arXiv commentSelected as the Best Student Paper Award for 2026 IVMSP

References in corpus (4)

• DeepPET: A deep encoder-decoder network for directly solving the PET reconstruction inverse problem
• A Survey of Stochastic Simulation and Optimization Methods in Signal Processing
• Score-Based Generative Models for PET Image Reconstruction
• Likelihood-Scheduled Score-Based Generative Modeling for Fully 3D PET Image Reconstruction