Classification of Axon Diameter Properties Using Machine Learning

Keywords

according acquisitions advantage allows although applied axon become biologically body brain characterize class classification classifier clinical complex component components composition computing conditions constraints contribution corpus curves datasets decay decays decreased describe diameter diffusion diffusivity dimension distributed distribution distributions done edges estimation evenly evident exist expected exploring extra fairly fascicles feature features fisher fitted five formulating fraction framework frameworks function functions future generated gradient great healthy highest hindered histological horizons imposing in vivo included increments inspecting intermediate learning linearly logistic machine many maps mathematical measure measured micro microscopic might model modeling multinomial narrow neurobiology noise noted numerous opened operations optimization perpendicular physical populations posed potential predefined prediction predicts previous principal probability problem projected properties protocol providing random rarely rather real regression regularized relevant repetitions require requires resolution restricted revealing robust roughly sampling scanned seems series setup simple simulated simultaneous smooth space spline statistical statistics structure studies subject subjects suggest trained training volume white wide