AUTHOR=Chen Lingdong , Yu Zhuo , Huang Jian , Shu Liqi , Kuosmanen Pekka , Shen Chen , Ma Xiaohui , Li Jing , Sun Chensheng , Li Zheming , Shu Ting , Yu Gang 

TITLE=Development of lung segmentation method in x-ray images of children based on TransResUNet

JOURNAL=Frontiers in Radiology

VOLUME=3

YEAR=2023

URL=https://www.frontiersin.org/journals/radiology/articles/10.3389/fradi.2023.1190745

DOI=10.3389/fradi.2023.1190745

ISSN=2673-8740

ABSTRACT=<sec><title>Background</title><p>Chest x-ray (CXR) is widely applied for the detection and diagnosis of children's lung diseases. Lung field segmentation in digital CXR images is a key section of many computer-aided diagnosis systems.</p></sec><sec><title>Objective</title><p>In this study, we propose a method based on deep learning to improve the lung segmentation quality and accuracy of children's multi-center CXR images.</p></sec><sec><title>Methods</title><p>The novelty of the proposed method is the combination of merits of TransUNet and ResUNet. The former can provide a self-attention module improving the feature learning ability of the model, while the latter can avoid the problem of network degradation.</p></sec><sec><title>Results</title><p>Applied on the test set containing multi-center data, our model achieved a Dice score of 0.9822.</p></sec><sec><title>Conclusions</title><p>This novel lung segmentation method proposed in this work based on TransResUNet is better than other existing medical image segmentation networks.</p></sec>