Semi-Supervised Learning of Mutually Accelerated MRI Synthesis without Fully-Sampled Ground Truths

TL;DR

This paper introduces a semi-supervised deep generative model for multi-contrast MRI synthesis that learns from accelerated, undersampled data without requiring fully-sampled ground truths, maintaining high quality and outperforming traditional methods.

Contribution

The paper presents a novel semi-supervised learning framework with multi-coil tensor losses that effectively synthesizes high-quality MRI contrasts from undersampled data without fully-sampled references.

Findings

Achieves performance comparable to fully-supervised models

Outperforms cascaded undersampled reconstruction approaches

Demonstrates robustness across neuroimaging datasets

Abstract

Learning-based synthetic multi-contrast MRI commonly involves deep models trained using high-quality images of source and target contrasts, regardless of whether source and target domain samples are paired or unpaired. This results in undesirable reliance on fully-sampled acquisitions of all MRI contrasts, which might prove impractical due to limitations on scan costs and time. Here, we propose a novel semi-supervised deep generative model that instead learns to recover high-quality target images directly from accelerated acquisitions of source and target contrasts. To achieve this, the proposed model introduces novel multi-coil tensor losses in image, k-space and adversarial domains. These selective losses are based only on acquired k-space samples, and randomized sampling masks are used across subjects to capture relationships among acquired and non-acquired k-space regions. Comprehensive experiments on multi-contrast neuroimaging datasets demonstrate that our semi-supervised approach yields equivalent performance to gold-standard fully-supervised models, while outperforming a cascaded approach that learns to synthesize based on reconstructions of undersampled data. Therefore, the proposed approach holds great promise to improve the feasibility and utility of accelerated MRI acquisitions mutually undersampled across both contrast sets and k-space.