Meeting Banner
Abstract #3395

Deep Learning Based Automatic Pipeline for Quantitative Assessment of Thigh Muscle Fatty Infiltration in Post-traumatic Osteoarthritis

Sibaji Gaj1, Brendan L. Eck1, Dongxing Xie1, Richard Lartey1, Charlotte Lo1, Mingrui Yang1, Kunio Nakamura1, Carl S. Winalski2, Kurt Spindler3, and Xiaojuan Li1
1Biomedical Engineering, Cleveland Clinic, Cleveland, OH, United States, 2Radiology, Cleveland Clinic, Cleveland, OH, United States, 3Orthopaedics, Cleveland Clinic, Cleveland, OH, United States

Synopsis

Quantitative assessment of thigh muscle morphology and fatty infiltration (FF%) in post-traumatic osteoarthritis is limited. In this work, we developed a deep learning based accurate segmentation method for muscles, bone and adipose tissue from thigh MRI and used these segmentation for automated quantification of FF and cross sectional area(CSA) of these tissues. 16 patients at 10 years after ACL reconstruction were studied. The proposed method showed significant improvement in segmentation metrics (Dice, Average surface distance (ASD)) and CSA compared with popular U-Net based deep learning models. For CSA and FF% quantification, automated methods had similar measurements compared with manual segmentation.

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.

Keywords