Abstract #3482

Supervised Machine Learning with Blind Source Separation (BSS) reveals distinct networks of pathological changes in brain magnetic susceptibility (QSM): Application to multiple sclerosis.

Ferdinand Schweser^1,2, Juliane Damm¹, Niels P Bergsland^1,3, Michael G Dwyer¹, Akshay V Dhamankar¹, Bianca Weinstock-Guttman⁴, and Robert Zivadinov^1,2

¹Buffalo Neuroimaging Analysis Center, Department of Neurology, Jacobs School of Medicine and Biomedical Sciences, University at Buffalo, The State University of New York, Buffalo, NY, United States, ²Center for Biomedical Imaging, Clinical and Translational Science Institute, University at Buffalo, The State University of New York, Buffalo, NY, United States, ³MR Research Laboratory, IRCCS, Don Gnocchi Foundation ONLUS, Milan, Italy, ⁴BairdMS Center, Department of Neurology, Jacobs School of Medicine and Biomedical Sciences, University at Buffalo, The State University of New York, Buffalo, NY, United States

Conventional region-of-interest (ROI) or voxel-based analyses of quantitative susceptibility maps (QSM) do not provide insights on the mechanistic and temporal independence of tissue alterations between subjects. In this study, we combined Blind Source Separation (BSS) with a Machine Learning strategy to reveal specific, independent disease-related networks of tissue alterations. Our analysis identified anatomically localized independent networks of pathological susceptibility alterations in multiple sclerosis (MS) without a priori information on age, sex, disease, or anatomy.

This abstract and the presentation materials are available to members only; a login is required.

Join Here