Meeting Banner
Abstract #1718

MRI signatures associated with pathologically relevant histological features of brain cancer at autopsy

Samuel Bobholz1, Allison Lowman2, Alexander Barrington3, Michael Brehler2, Sean McGarry1, Jennifer Connelly4, Elizabeth Cochran5, Anjishnu Banerjee6, and Peter LaViolette2,3
1Biophysics, Medical College of Wisconsin, Wauwatosa, WI, United States, 2Radiology, Medical College of Wisconsin, Wauwatosa, WI, United States, 3Biomedical Engineering, Medical College of Wisconsin, Wauwatosa, WI, United States, 4Neurology, Medical College of Wisconsin, Wauwatosa, WI, United States, 5Pathology, Medical College of Wisconsin, Wauwatosa, WI, United States, 6Biostatistics, Medical College of Wisconsin, Wauwatosa, WI, United States

This study sought to assess the ability for voxel-wise MRI intensity values to distinguish between co-registered pathological annotations of autopsy tissue samples from brain cancer patients. Though single image and pairwise image assessments did not reveal separable intensity distributions for the pathological annotation classes, ensemble-based predictive modelling using multiparametric MRI intensities proved able to predict pathological annotations with modest accuracy. These results suggest a complex relationship between MRI values and pathological features that are most accurately assessed in terms of multiple MR imaging modalities.

This abstract and the presentation materials are available to 2020 meeting attendees and eLibrary customers only; a login is required.

Join Here