Robustly segmenting quadriceps muscles of ultra-endurance athletes with weakly supervised U-Net

Hoai-Thu Nguyen, Pierre Croisille, Magalie Viallon, Sarah Leclerc, Sylvain Grange, Rémi Grange, Olivier Bernard, Thomas Grenier

Keywords: unet, weakly supervised, medical image segmentation

TL;DR: Segmentation of quadriceps muscle heads with UNet and corrective learning

Abstract: In this study, segmentation of quadriceps muscle heads of ultra-endurance athletes was done using a multi-atlas segmentation and corrective leaning framework where the registration based multi-atlas segmentation step was replaced with weakly supervised U-Net. For the case with remarkably different morphology, our method produced improved accuracy, while reduced signicantly the computation time.

Code Of Conduct: I have read and accept the code of conduct.

Remove If Rejected: Remove submission from public view if paper is rejected.