Meeting Banner
Abstract #0040

Diffusion Histology Imaging Classifies Lesions in Multiple Sclerosis

Zezhong Ye1, Ajit George1, Anthony T. Wu2, Xuan Niu1, Joshua Lin3, Gautam Adusumilli4, Robert T. Naismith4, Anne H. Cross4, Peng Sun1, and Sheng-Kwei Song1
1Radiology, Washington University School of Medicine, Saint Louis, MO, United States, 2Biomedical Engineering, Washington University, Saint Louis, MO, United States, 3Keck School of Medicine, The University of Southern California, Los Angeles, CA, United States, 4Neurology, Washington University School of Medicine, Saint Louis, MO, United States

MS lesions have heterogeneous pathology, including inflammation, demyelination, axonal injury, and neuronal loss. Our laboratory has developed a diffusion basis spectrum imaging (DBSI) technique to address the shortcomings of MRI-based MS. Primary DBSI metrics have been demonstrated to be associated with MS pathologies in animal models and human tissue. We propose that profiles of multiple DBSI metrics can identify important patterns within MS lesions and normal appearing white matter. Here we report that Diffusion Histology Imaging (DHI), an improved approach that combines a deep neural network (DNN) algorithm with DBSI-derived diffusion metrics, accurately detected and classified various MS lesion subtypes.

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

Join Here