QSMDiff: Unsupervised 3D Diffusion Models for Quantitative Susceptibility Mapping

TL;DR

QSMDiff is an unsupervised 3D diffusion model that improves quantitative susceptibility mapping from MRI data, offering robust, high-quality reconstructions across various scan parameters without supervised training.

Contribution

The paper introduces QSMDiff, a novel unsupervised 3D diffusion model for QSM that enhances generalizability and integrates super-resolution and denoising tasks.

Findings

Outperforms existing methods on simulated and in-vivo data

Effective across different MRI sequences and acquisition parameters

Enables robust 3D QSM reconstruction with high quality

Abstract

Quantitative Susceptibility Mapping (QSM) dipole inversion is an ill-posed inverse problem for quantifying magnetic susceptibility distributions from MRI tissue phases. While supervised deep learning methods have shown success in specific QSM tasks, their generalizability across different acquisition scenarios remains constrained. Recent developments in diffusion models have demonstrated potential for solving 2D medical imaging inverse problems. However, their application to 3D modalities, such as QSM, remains challenging due to high computational demands. In this work, we developed a 3D image patch-based diffusion model, namely QSMDiff, for robust QSM reconstruction across different scan parameters, alongside simultaneous super-resolution and image-denoising tasks. QSMDiff adopts unsupervised 3D image patch training and full-size measurement guidance during inference for controlled image generation. Evaluation on simulated and in-vivo human brains, using gradient-echo and echo-planar imaging sequences across different acquisition parameters, demonstrates superior performance. The method proposed in QSMDiff also holds promise for impacting other 3D medical imaging applications beyond QSM.