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 Rajamohan^3,4, Katherine Medina^3,5, Smita Rao⁶, Cem Deniz^3,5, and Ryan Brown^3,5

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.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.