Reproduce “Automated Muscle Segmentation from Clinical CT using Bayesian U-Net for Personalized Musculoskeletal Modeling” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Yuta Hiasa, Yoshito Otake, Masaki Takao, Takeshi Ogawa, Nobuhiko Sugano, Yoshinobu Sato
The authors develop a U-Net-based method to segment 19 hip and thigh muscles in CT and estimate segmentation uncertainty using repeated predictions with dropout. In leave-one-out cross-validation on 20 annotated scans, it achieved mean Dice coefficient 0.891 ± 0.016 and average symmetric surface distance 0.994 ± 0.230 mm, outperforming hierarchical multi-atlas segmentation. Uncertainty-guided annotation gains were demonstrated only in simulation.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.