Joint Diffusion: Mutual Consistency-Driven Diffusion Model for PET-MRI Co-Reconstruction

TL;DR

This paper introduces MC-Diffusion, a novel joint PET-MRI reconstruction model that leverages mutual consistency to improve image quality and accelerate MRI, outperforming existing methods.

Contribution

The study presents a new diffusion-based model that learns the joint distribution of PET and MRI images, utilizing their complementary information for enhanced reconstruction.

Findings

MC-Diffusion outperforms state-of-the-art methods in qualitative assessments.

Quantitative metrics show significant improvements with MC-Diffusion.

Experiments on ADNI dataset validate the effectiveness of the proposed approach.

Abstract

Positron Emission Tomography and Magnetic Resonance Imaging (PET-MRI) systems can obtain functional and anatomical scans. PET suffers from a low signal-to-noise ratio. Meanwhile, the k-space data acquisition process in MRI is time-consuming. The study aims to accelerate MRI and enhance PET image quality. Conventional approaches involve the separate reconstruction of each modality within PET-MRI systems. However, there exists complementary information among multi-modal images. The complementary information can contribute to image reconstruction. In this study, we propose a novel PET-MRI joint reconstruction model employing a mutual consistency-driven diffusion mode, namely MC-Diffusion. MC-Diffusion learns the joint probability distribution of PET and MRI for utilizing complementary information. We conducted a series of contrast experiments about LPLS, Joint ISAT-net and MC-Diffusion by the ADNI dataset. The results underscore the qualitative and quantitative improvements achieved by MC-Diffusion, surpassing the state-of-the-art method.