A CT-Based Airway Segmentation Using U$^2$-net Trained by the Dice Loss Function
This work addresses airway segmentation for pulmonary disease diagnosis, but it is incremental as it applies an existing method to a specific dataset with refinements.
The paper tackled airway segmentation from chest CT scans using a U^2-net trained with Dice loss, achieving good accuracy and connectivity in segmented airway trees on validation data from multi-site scans.
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.