Abrar Faiyaz1, Marvin M Doyley1,2,3, Giovanni Schifitto2,4, Jianhui Zhong2,3,5, and Md Nasir Uddin4
1Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY, United States, 2Department of Imaging Sciences, University of Rochester, Rochester, NY, United States, 3Department of Biomedical Engineering, University of Rochester, Rochester, NY, United States, 4Department of Neurology, University of Rochester, Rochester, NY, United States, 5Department of Physics and Astronomy, University of Rochester, Rochester, NY, United States
1Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY, United States, 2Department of Imaging Sciences, University of Rochester, Rochester, NY, United States, 3Department of Biomedical Engineering, University of Rochester, Rochester, NY, United States, 4Department of Neurology, University of Rochester, Rochester, NY, United States, 5Department of Physics and Astronomy, University of Rochester, Rochester, NY, United States
The study enables single-shell fISO estimation with FA and T2 weighted non-diffusion signal-based sparse dictionary, and utilizes a Deep Learner-based NODDI framework for single-shell NDI and ODI estimation comparable with multi-shell NODDI (error <5%).
Figure 2: A) HSV (Hue, Saturation, Value) maps generated with fISO, ODI and NDI in respective channels- H, S and V shows single- and multi-shell maps generated with DLpN and NODDI. B) shows HSV channels and C) shows colormap for fISO and overall HSV space.
Figure 5: Comparison of single-shell DLpN with P2 (DLpNP2) and multi-shell NODDI (NODDIPall) that reported minimum error, shows noisy estimation from multi-shell could be addressed with DLpN single-shell reconstructed NDI. White arrows show some regions with noisy overestimation in NODDIPall NDI.