CT evaluation of 2D and 3D holistic deep learning methods for the volumetric segmentation of airway lesions
It addresses segmentation of cystic fibrosis lesions for clinical application, but is incremental as it compares and refines existing deep learning methods.
This study compared 2D and 3D deep learning models for segmenting airway lesions in cystic fibrosis CT scans, finding that the 3D model performed better, and improved the 2D model with a specialized loss function, validated against pulmonary function tests.
This research embarked on a comparative exploration of the holistic segmentation capabilities of Convolutional Neural Networks (CNNs) in both 2D and 3D formats, focusing on cystic fibrosis (CF) lesions. The study utilized data from two CF reference centers, covering five major CF structural changes. Initially, it compared the 2D and 3D models, highlighting the 3D model's superior capability in capturing complex features like mucus plugs and consolidations. To improve the 2D model's performance, a loss adapted to fine structures segmentation was implemented and evaluated, significantly enhancing its accuracy, though not surpassing the 3D model's performance. The models underwent further validation through external evaluation against pulmonary function tests (PFTs), confirming the robustness of the findings. Moreover, this study went beyond comparing metrics; it also included comprehensive assessments of the models' interpretability and reliability, providing valuable insights for their clinical application.