Fig. 3: The example airway trees obtained by segmentation using three different methods.
From: Automated detection of radiolucent foreign body aspiration on chest CT using deep learning
The first column shows the gold standard (reference label), while the second, third, and fourth columns depict airway trees reconstructed using the MedSeg, MedpSeg, and AG-UNet (Connectivity-Aware) methods, respectively. In the visualizations, red represents the model prediction, blue indicates the overlap between the model prediction and the gold standard, and green denotes the gold standard.
