Contrastive Diffusion Model with Auxiliary Guidance for Coarse-to-Fine PET Reconstruction

TL;DR

This paper introduces a coarse-to-fine diffusion-based PET reconstruction method that improves speed and image correspondence by combining a deterministic coarse prediction with iterative refinement, guided by auxiliary and contrastive strategies.

Contribution

It proposes a novel coarse-to-fine framework with auxiliary guidance and contrastive diffusion strategies to enhance PET image reconstruction from low-dose scans.

Findings

Outperforms state-of-the-art PET reconstruction methods.

Significantly improves sampling speed.

Enhances correspondence between LPET and RPET images.

Abstract

To obtain high-quality positron emission tomography (PET) scans while reducing radiation exposure to the human body, various approaches have been proposed to reconstruct standard-dose PET (SPET) images from low-dose PET (LPET) images. One widely adopted technique is the generative adversarial networks (GANs), yet recently, diffusion probabilistic models (DPMs) have emerged as a compelling alternative due to their improved sample quality and higher log-likelihood scores compared to GANs. Despite this, DPMs suffer from two major drawbacks in real clinical settings, i.e., the computationally expensive sampling process and the insufficient preservation of correspondence between the conditioning LPET image and the reconstructed PET (RPET) image. To address the above limitations, this paper presents a coarse-to-fine PET reconstruction framework that consists of a coarse prediction module (CPM) and an iterative refinement module (IRM). The CPM generates a coarse PET image via a deterministic process, and the IRM samples the residual iteratively. By delegating most of the computational overhead to the CPM, the overall sampling speed of our method can be significantly improved. Furthermore, two additional strategies, i.e., an auxiliary guidance strategy and a contrastive diffusion strategy, are proposed and integrated into the reconstruction process, which can enhance the correspondence between the LPET image and the RPET image, further improving clinical reliability. Extensive experiments on two human brain PET datasets demonstrate that our method outperforms the state-of-the-art PET reconstruction methods. The source code is available at \url{https://github.com/Show-han/PET-Reconstruction}.