Abstract #1309

Transfer Learning in Hip MRI Segmentation: Geometry Is More Important Than Contrast

Claudia Iriondo^1,2, Michael Girard³, Valentina Pedoia¹, and Sharmila Majumdar¹

¹Radiology and Biomedical Imaging, University of California, San Francsico, San Francisco, CA, United States, ²Bioengineering, University of California, Berkeley, Berkeley, CA, United States, ³Center for Digital Health Innovation, University of California, San Francsico, San Francisco, CA, United States

Transfer learning for medical image segmentation tasks is a promising technique that has the potential to overcome the challenges posed by limited training data. In this study we investigate the contribution of geometrically-similar and contrast-similar features for transfer learning to a hip MR segmentation task. We show pretraining with a geometrically similar task leads to more rapid convergence, can stabilize segmentation accuracy as datasets become reduced in size, and leads to more reliable biomarker extraction.

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

Join Here