A comparative analysis of deep learning models for lung segmentation on X-ray images

In the field of medical imaging, accurate segmentation of lungs on X-rays is important in many applications [6], from early disease detection to treatment planning and patient monitoring. As healthcare evolves, the need for fast and accurate tools grows, implying physician support with deep learning approaches [5]. In particular, solutions such as U-Net demonstrate the potential to automate the task of lung segmentation, offering promising advances in improved accuracy [8]. However, despite these advances, the inevitable diversity of X-ray images makes it difficult for some modern segmentation methods to deal with them. Although many solutions show high performance in simple and typical cases, their performance degrades when confronted with complex ones. Moreover, the issue of using pre-trained models on images with different characteristics may have potential negative consequences when used for real-world solutions [3]. Recognizing these challenges, our objective is to analyze existing solutions for lung segmentation and systematically evaluate their performance across a dataset of varying characteristics. In this study, we analyze and compare three prominent methods - Lung VAE, TransResUNet, and CE-Net - using five image modifications. The ultimate goal is to determine the most accurate method for lung segmentation in diverse scenarios.