Accurate parameter estimation using scan-specific unsupervised deep learning for relaxometry and MR fingerprinting

TL;DR

This paper introduces an unsupervised CNN that leverages signal physics and spatial information to improve relaxation parameter estimation in MRI, achieving higher accuracy and robustness than traditional methods.

Contribution

The novel CNN integrates Bloch simulations and residual learning for MRI relaxometry, enhancing estimation accuracy and enabling high-quality T1 and T2 mapping from undersampled data.

Findings

Significantly improved quantification accuracy over standard methods

Enhanced robustness to noise in relaxation parameter estimation

Successful application to high-quality T1 and T2 mapping from undersampled MRI data

Abstract

We propose an unsupervised convolutional neural network (CNN) for relaxation parameter estimation. This network incorporates signal relaxation and Bloch simulations while taking advantage of residual learning and spatial relations across neighboring voxels. Quantification accuracy and robustness to noise is shown to be significantly improved compared to standard parameter estimation methods in numerical simulations and in vivo data for multi-echo T2 and T2* mapping. The combination of the proposed network with subspace modeling and MR fingerprinting (MRF) from highly undersampled data permits high quality T1 and T2 mapping.