Abstract #1136
Deep Learning and Fat Fraction Based Analysis of Calf MRI in Diabetic Patients Following Exercise Intervention
Jill T Shah1, Tanay T Shah2, Haresh R Rajamohan3,4, Katherine Medina3,5, Smita Rao6, Cem Deniz3,5, and Ryan Brown3,5
1NYU Grossman School of Medicine, New York University, New York, NY, United States, 2College of Arts and Sciences, New York University, New York, NY, United States, 3Center for Biomedical Imaging, Department of Radiology, New York University Grossman School of Medicine, New York, NY, United States, 4Center for Data Science, New York University, New York, NY, United States, 5Center for Advanced Imaging Innovation and Research (CAI2R), Department of Radiology, New York University Grossman School of Medicine, New York, NY, United States, 6Department of Physical Therapy, New York University, New York, NY, United States
Synopsis
Diabetic peripheral neuropathy (DPN) is characterized by increased adiposity implicated in metabolic dysfunction. Proton-based Dixon MRI is an appropriate means to quantify adiposity, but analysis requires time-consuming manual image segmentation. To address this problem, we developed an automated segmentation algorithm based on convolutional neural networks that provided high dice similarity coefficient scores (>0.88) on multiple regions of interest (ROI) within the calf. We utilized the networks to analyze fat fraction trends in individuals with DPN following a 10-week supervised exercise program. We measured decreased adiposity in the combined calf interstitial and muscle space (P<0.1) but not in individual muscle ROIs.
This abstract and the presentation materials are available to members only;
a login is required.
Join Here
