An Effective Deep Neural Network for Lung Lesions Segmentation From COVID-19 CT Images

• Published in: IEEE transactions on industrial informatics 2021-09, Vol.17 (9), p.6528-6538
• Main Authors: Chen, Cheng, Zhou, Kangneng, Zha, Muxi, Qu, Xiangyan, Guo, Xiaoyu, Chen, Hongyu, Wang, Zhiliang, Xiao, Ruoxiu
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Computed tomography; Conditional random field; Conditional random fields; Coronaviruses; COVID-19; data augmentation; deep network; Feature extraction; Image segmentation; Lesions; Lung; lung lesions segmentation; Lungs; Medical imaging; Optimization; Resampling; Three dimensional models; Three-dimensional displays
• ISSN: 1551-3203; 1941-0050
• DOI: 10.1109/TII.2021.3059023

Automatic segmentation of lung lesions from COVID-19 computed tomography (CT) images can help to establish a quantitative model for diagnosis and treatment. For this reason, this article provides a new segmentation method to meet the needs of CT images processing under COVID-19 epidemic. The main steps are as follows: First, the proposed region of interest extraction implements patch mechanism strategy to satisfy the applicability of 3-D network and remove irrelevant background. Second, 3-D network is established to extract spatial features, where 3-D attention model promotes network to enhance target area. Then, to improve the convergence of network, a combination loss function is introduced to lead gradient optimization and training direction. Finally, data augmentation and conditional random field are applied to realize data resampling and binary segmentation. This method was assessed with some comparative experiment. By comparison, the proposed method reached the highest performance. Therefore, it has potential clinical applications.