A comparative analysis of deep learning models for lung segmentation on X-ray images
This work provides a comparative analysis for medical imaging researchers, but it is incremental as it evaluates existing methods without introducing new ones.
The study compared deep learning models for lung segmentation in X-ray images, finding that CE-Net achieved the best performance with the highest dice similarity coefficient and intersection over union metrics.
Robust and highly accurate lung segmentation in X-rays is crucial in medical imaging. This study evaluates deep learning solutions for this task, ranking existing methods and analyzing their performance under diverse image modifications. Out of 61 analyzed papers, only nine offered implementation or pre-trained models, enabling assessment of three prominent methods: Lung VAE, TransResUNet, and CE-Net. The analysis revealed that CE-Net performs best, demonstrating the highest values in dice similarity coefficient and intersection over union metric.