A CT-Based Airway Segmentation Using U$^2$-net Trained by the Dice Loss Function

TL;DR

This paper presents a U$^2$-net based method trained with Dice loss for airway segmentation from chest CT scans, demonstrating improved accuracy and connectivity in airway tree modeling.

Contribution

It introduces a novel application of U$^2$-net trained with Dice loss for airway segmentation, enhancing accuracy and connectivity over previous methods.

Findings

Majority of segmented airway trees show good accuracy and connectivity.

Refinement techniques improve the quality of airway tree models.

Method performs well on multi-site CT scan data.

Abstract

Airway segmentation from chest computed tomography scans has played an essential role in the pulmonary disease diagnosis. The computer-assisted airway segmentation based on the U-net architecture is more efficient and accurate compared to the manual segmentation. In this paper we employ the U$^2$-net trained by the Dice loss function to model the airway tree from the multi-site CT scans based on 299 training CT scans provided by the ATM'22. The derived saliency probability map from the training is applied to the validation data to extract the corresponding airway trees. The observation shows that the majority of the segmented airway trees behave well from the perspective of accuracy and connectivity. Refinements such as non-airway regions labeling and removing are applied to certain obtained airway tree models to display the largest component of the binary results.