Lesion probability mapping in MS patients using a regression network on MR Fingerprinting

Abstract

Purpose To develop a regression neural network for the reconstruction of lesion probability maps on Magnetic Resonance Fingerprinting using echo-planar imaging (MRF-EPI) in addition to T 1 , T 2 * , NAWM, and GM- probability maps. Methods We performed MRF-EPI measurements in 42 patients with multiple sclerosis and 6 healthy volunteers along two sites. A U-net was trained to reconstruct the denoised and distortion corrected T 1 and T 2 * maps, and to additionally generate NAWM-, GM-, and WM lesion probability maps. Results WM lesions were predicted with a dice coefficient of 0.61±0.09 and a lesion detection rate of 0.85±0.25 for a threshold of 33%. The network jointly enabled accurate T 1 and T 2 * times with relative deviations of 5.2% and 5.1% and average dice coefficients of 0.92±0.04 and 0.91±0.03 for NAWM and GM after binarizing with a threshold of 80%. Conclusion DL is a promising tool for the prediction of lesion probability maps in a fraction of time. These might be of clinical interest for the WM lesion analysis in MS patients.

Inline dual‐echo T2 quantification in brain using a fast mapping reconstruction technique

“…However, as shown in this study, the PD‐T2 method based on robust Bloch simulations is fast enough to produce individualized inline images without requiring training data. Finally, magnetic resonance fingerprinting (MRF) is emerging as a valuable and rapid technique for many different quantitative measures including T1, T2, and T2* 28–30 with the ability for inline maps. Previous studies have investigated reproducibility and different acquisition strategies, although work is needed to compare MRF with gold standard quantification values 18 .…”