CT evaluation of 2D and 3D holistic deep learning methods for the volumetric segmentation of airway lesions

TL;DR

This study compares 2D and 3D CNN-based deep learning methods for volumetric segmentation of airway lesions in cystic fibrosis, demonstrating the 3D model's superior performance and exploring improvements to 2D models for clinical use.

Contribution

It provides a comparative analysis of 2D and 3D CNN models for airway lesion segmentation in CF, introducing a loss function adaptation to enhance 2D model accuracy.

Findings

3D models outperform 2D in capturing complex airway features

Loss adaptation improves 2D model accuracy significantly

Models validated against pulmonary function tests confirming robustness

Abstract

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.