Lung segmentation on CT images is a crucial step for a computer-aided diagnosis system of lung diseases. The existing deep learning based lung segmentation methods are less efficient to segment lungs on clinical CT images, especially that the segmentation on lung boundaries is not accurate enough due to complex pulmonary opacities in practical clinics. In this paper, we propose a boundary-guided network (BG-Net) to address this problem. It contains two auxiliary branches that seperately segment lungs and extract the lung boundaries, and an aggregation branch that efficiently exploits lung boundary cues to guide the network for more accurate lung segmentation on clinical CT images. We evaluate the proposed method on a private dataset collected from the Osaka university hospital and four public datasets including StructSeg, HUG, VESSEL12, and a Novel Coronavirus 2019 (COVID-19) dataset. Experimental results show that the proposed method can segment lungs more accurately and outperform several other deep learning based methods.

[1]  Rui Xu, Yi Wang, Tiantian Liu, Xinchen Ye*, Lin Lin, Yen-wei Chen, Shoji Kido, Noriyuki Tomiyama, "BG-Net: Boundary-Guided Network for Lung Segmentation on Clinical CT Images", International Conference on Pattern Recognition (ICPR), Mila, Italy, January 10-15, 2021. (CCF-C)

[2]  Rui Xu, Jiao Pan, Xinchen Ye, Yasuhi Hirano, Shoji Kido, Satoshi Tanaka, A pilot study to utilize a deep convolutional network to segment lungs with complex opacities, 2017 Chinese Automation Congress :3291-3295, 2017.