The purpose of this work was to develop an MRI-based classifier of neurofibrillary tangles by combining ex-vivo MRI and detailed neuropathology in brain autopsies from a large number (N=878) of community-based older adults. The ex-vivo classifier was trained on volumetric, cortical thickness, subcortical shape, diffusion, and R2 measurements, as well as age and sex. The average AUC of the final classifier was 0.87. Future work will convert the ex-vivo classifier to in-vivo and test it in-vivo in independent cohorts of older adults.
This abstract and the presentation materials are available to members only; a login is required.