Phy-Diff: Physics-guided Hourglass Diffusion Model for Diffusion MRI Synthesis

TL;DR

This paper introduces Phy-Diff, a physics-guided diffusion model that incorporates physical principles and anatomical priors to generate high-quality diffusion MRI, improving over existing methods in diversity and relevance.

Contribution

The study presents a novel diffusion model that integrates physical principles and white matter tract priors for more accurate and detailed dMRI synthesis.

Findings

Outperforms state-of-the-art methods in dMRI generation

Incorporates physical principles into the diffusion process

Uses white matter tract priors to enhance anatomical details

Abstract

Diffusion MRI (dMRI) is an important neuroimaging technique with high acquisition costs. Deep learning approaches have been used to enhance dMRI and predict diffusion biomarkers through undersampled dMRI. To generate more comprehensive raw dMRI, generative adversarial network based methods are proposed to include b-values and b-vectors as conditions, but they are limited by unstable training and less desirable diversity. The emerging diffusion model (DM) promises to improve generative performance. However, it remains challenging to include essential information in conditioning DM for more relevant generation, i.e., the physical principles of dMRI and white matter tract structures. In this study, we propose a physics-guided diffusion model to generate high-quality dMRI. Our model introduces the physical principles of dMRI in the noise evolution in the diffusion process and introduce a query-based conditional mapping within the difussion model. In addition, to enhance the anatomical fine detials of the generation, we introduce the XTRACT atlas as prior of white matter tracts by adopting an adapter technique. Our experiment results show that our method outperforms other state-of-the-art methods and has the potential to advance dMRI enhancement.