Hierarchical Loss And Geometric Mask Refinement For Multilabel Ribs Segmentation
arXiv:2405.15500
Abstract
Automatic ribs segmentation and numeration can increase computed tomography assessment speed and reduce radiologists mistakes. We introduce a model for multilabel ribs segmentation with hierarchical loss function, which enable to improve multilabel segmentation quality. Also we propose postprocessing technique to further increase labeling quality. Our model achieved new state-of-the-art 98.2% label accuracy on public RibSeg v2 dataset, surpassing previous result by 6.7%.
Accepted to IEEE ISBI 2024