Accelerated white matter lesion analysis based on simultaneous T1 and T2∗ quantification using magnetic resonance fingerprinting and deep learning

Abstract

Purpose: To develop an accelerated postprocessing pipeline for reproducible and efficient assessment of white matter lesions using quantitative magnetic resonance fingerprinting (MRF) and deep learning.

Methods: MRF using echo-planar imaging (EPI) scans with varying repetition and echo times were acquired for whole brain quantification of $T_1$ and $T_2^{\ast }$ in 50 subjects with multiple sclerosis (MS) and 10 healthy volunteers along 2 centers. MRF $T_1$ and $T_2^{\ast }$ parametric maps were distortion corrected and denoised. A CNN was trained to reconstruct the $T_1$ and $T_2^{\ast }$ parametric maps, and the WM and GM probability maps.

Results: Deep learning-based postprocessing reduced reconstruction and image processing times from hours to a few seconds while maintaining high accuracy, reliability, and precision. Mean absolute error performed the best for $T_1$ (deviations 5.6%) and the logarithmic hyperbolic cosinus loss the best for $T_2^{\ast }$ (deviations 6.0%).

Conclusions: MRF is a fast and robust tool for quantitative $T_1$ and $T_2^{\ast }$ mapping. Its long reconstruction and several postprocessing steps can be facilitated and accelerated using deep learning.

Keywords: $T_1$ mapping; $T_2^{\ast }$ mapping; deep learning reconstruction; magnetic resonance fingerprinting.