Abstract #0337

Automatic Segmentation of Hip Cartilage with Deep Convolutional Neural Nets for the evaluation of Acetabulum and Femoral T1ρ and T2 relaxation times.

Michael Girard¹, Valentina Pedoia², Berk Norman², Jasmine Rossi-Devries², and Sharmila Majumdar²

¹Center for Digital Health Innovation, University of California, San Francisco, San Francisco, CA, United States, ²Department of Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, CA, United States

In this study we utilize a deep learning approach to automatically segment the femoral and acetabular cartilages in the hip. From these segmentations we also calculate T1ρ and T2 relaxation times then compare to manual segmentations and their T1ρ and T2 values. We show the T1ρ and T2 relaxation times, calculated using manual and automatic segmentations, are very correlated, R values above .94, and comparable.

This abstract and the presentation materials are available to members only; a login is required.

Join Here