eess.IVAug 29, 2026

Manifold-Constrained PET Reconstruction with Learned Flow-Matching Priors

Authors: Hengjia Ran, Jie Luo, Yutao Zhu, Rui Hu, Fenglin Zhan, Jianyong Jiang, Huafeng Liu, Bo Zhao

Organizations: ZJU-UIUC Institute, Zhejiang University, Haining 314400, China · College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China · College of Optical Science and Engineering, Zhejiang University, Hangzhou 310027, China · Vivo Mobile Communication Co., Ltd., Hangzhou 311100, China · 

Abstract

Image reconstruction for positron emission tomography (PET) is an ill-posed Poisson inverse problem. In this work, we introduce an unsupervised, optimization-based reconstruction framework that employs a flow-matching generative model as a learned manifold prior. We train the generative model on high-quality PET images to learn a differentiable ordinary differential equation (ODE)-based transport from a Gaussian latent distribution to the PET image distribution. We incorporate this generator as an explicit manifold constraint into a regularized Poisson likelihood formulation. To solve the resulting problem, we develop an alternating direction method of multipliers (ADMM) algorithm that integrates an expectation-maximization (EM)-type surrogate update for Poisson data fidelity with gradient-based latent-space optimization. Numerical simulations and in vivo PET experiments demonstrate improved reconstruction accuracy compared with conventional reconstruction methods and recent deep learning-based approaches, particularly in low-count settings, with competitive computational efficiency.

Figures & tables

Explore similar work

CardsList
  1. Bayesian PET Reconstruction with Learned Flow Matching Priors via Langevin Sampling

    Oct 30, 2026Hengjia Ran, Huafeng Liu, Bo ZhaoImage ReconstructionBayesian Inverse Problems

  2. Flow Matching-Based PET Image Reconstruction

    Aug 20, 2026Fumio Hashimoto, Ziqian Huang, Tatsuya Yokota +1Image ReconstructionFlow Matching

  3. FlowPET: Physics-Informed Symplectic Flow Matching for Low-Count PET Reconstruction

    Jul 13, 2026Zheng Zhang, Hao Tang, Yingying Hu +2Flow MatchingImage Reconstruction