Meta-Learning Enabled Score-Based Generative Model for 1.5T-Like Image Reconstruction from 0.5T MRI

TL;DR

This paper introduces a meta-learning framework with a teacher-student mechanism to reconstruct high-field-like MRI images from low-field MRI data, addressing the challenge of unpaired data and ill-posed inverse problems.

Contribution

A novel meta-learning approach using a teacher-student setup to generate pseudo-paired data and improve high-field MRI reconstruction from low-field images.

Findings

Outperforms state-of-the-art unpaired learning methods on real data.

Effectively models the degradation process with an optimal-transport-driven teacher.

Enhances image quality in low-field MRI reconstruction.

Abstract

Magnetic resonance imaging (MRI) is known to have reduced signal-to-noise ratios (SNR) at lower field strengths, leading to signal degradation when producing a low-field MRI image from a high-field one. Therefore, reconstructing a high-field-like image from a low-field MRI is a complex problem due to the ill-posed nature of the task. Additionally, obtaining paired low-field and high-field MR images is often not practical. We theoretically uncovered that the combination of these challenges renders conventional deep learning methods that directly learn the mapping from a low-field MR image to a high-field MR image unsuitable. To overcome these challenges, we introduce a novel meta-learning approach that employs a teacher-student mechanism. Firstly, an optimal-transport-driven teacher learns the degradation process from high-field to low-field MR images and generates pseudo-paired high-field and low-field MRI images. Then, a score-based student solves the inverse problem of reconstructing a high-field-like MR image from a low-field MRI within the framework of iterative regularization, by learning the joint distribution of pseudo-paired images to act as a regularizer. Experimental results on real low-field MRI data demonstrate that our proposed method outperforms state-of-the-art unpaired learning methods.