1. Lesion probability mapping in MS patients using a regression network on MR fingerprinting
- Author
-
Achim Gass, Ralf R. Schmidt, Ingo Hermann, Lothar R. Schad, Frank G. Zöllner, Alena-Kathrin Golla, Sara Llufriu, Elisabeth Solana, and Eloy Martinez-Heras
- Subjects
Multiple Sclerosis ,T Mapping ,030218 nuclear medicine & medical imaging ,Lesion ,03 medical and health sciences ,0302 clinical medicine ,Nuclear magnetic resonance ,Deep Learning ,Sørensen–Dice coefficient ,Leukoencephalopathies ,$$T_1$$ T 1 Mapping ,Healthy volunteers ,medicine ,Medical technology ,Humans ,Radiology, Nuclear Medicine and imaging ,R855-855.5 ,Lesion prediction ,Mathematics ,Probability ,Deep learning reconstruction ,Brain Mapping ,Magnetic resonance fingerprinting ,medicine.diagnostic_test ,Lesion detection ,Echo-Planar Imaging ,Network on ,Magnetic resonance imaging ,Probability mapping ,White Matter ,Regression ,\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$${T_2}^*$$\end{document}T2∗ Mapping ,Technical Advance ,$${T_2}^*$$ T 2 ∗ Mapping ,T* Mapping ,\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$T_1$$\end{document}T1 Mapping ,Neural Networks, Computer ,medicine.symptom ,030217 neurology & neurosurgery - Abstract
Background 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 1 , $${T_2}^*$$ 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 $$T_1$$ T 1 and $${T_2}^*$$ T 2 ∗ maps, and to additionally generate NAWM-, GM-, and WM lesion probability maps. Results WM lesions were predicted with a dice coefficient of $$0.61\pm 0.09$$ 0.61 ± 0.09 and a lesion detection rate of $$0.85\pm 0.25$$ 0.85 ± 0.25 for a threshold of 33%. The network jointly enabled accurate $$T_1$$ T 1 and $${T_2}^*$$ T 2 ∗ times with relative deviations of 5.2% and 5.1% and average dice coefficients of $$0.92\pm 0.04$$ 0.92 ± 0.04 and $$0.91\pm 0.03$$ 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.
- Published
- 2021