Only-Train-Once MR Fingerprinting for Magnetization Transfer Contrast Quantification

TL;DR

This paper introduces an innovative 'Only-Train-Once' MR fingerprinting framework that accurately quantifies tissue parameters across various MRF schedules without retraining, streamlining MTC-MRF imaging.

Contribution

The study presents a flexible, recurrent neural network-based OTOM framework that eliminates the need for schedule-specific training in MTC-MRF, enabling efficient and accurate tissue parameter estimation.

Findings

Achieves accurate water and MTC parameter quantification across multiple MRF schedules.

Demonstrates excellent agreement with traditional deep learning and fitting methods.

Applicable to digital phantoms and in vivo data, showing robustness and versatility.

Abstract

Magnetization transfer contrast magnetic resonance fingerprinting (MTC-MRF) is a novel quantitative imaging technique that simultaneously measures several tissue parameters of semisolid macromolecule and free bulk water. In this study, we propose an Only-Train-Once MR fingerprinting (OTOM) framework that estimates the free bulk water and MTC tissue parameters from MR fingerprints regardless of MRF schedule, thereby avoiding time-consuming process such as generation of training dataset and network training according to each MRF schedule. A recurrent neural network is designed to cope with two types of variants of MRF schedules: 1) various lengths and 2) various patterns. Experiments on digital phantoms and in vivo data demonstrate that our approach can achieve accurate quantification for the water and MTC parameters with multiple MRF schedules. Moreover, the proposed method is in excellent agreement with the conventional deep learning and fitting methods. The flexible OTOM framework could be an efficient tissue quantification tool for various MRF protocols.