Hierarchical Loss And Geometric Mask Refinement For Multilabel Ribs Segmentation

TL;DR

This paper presents a new hierarchical loss function and a postprocessing technique for multilabel ribs segmentation in CT scans, achieving state-of-the-art accuracy and improving the speed and reliability of radiological assessments.

Contribution

The paper introduces a novel hierarchical loss function and a postprocessing method that significantly enhance multilabel ribs segmentation accuracy.

Findings

Achieved 98.2% label accuracy on RibSeg v2 dataset

Surpassed previous state-of-the-art by 6.7%

Improves segmentation quality and assessment speed

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%.