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

被引:56
作者
Chen, Cheng [1 ]
Zhou, Kangneng [1 ]
Zha, Muxi [1 ]
Qu, Xiangyan [1 ]
Guo, Xiaoyu [1 ]
Chen, Hongyu [1 ]
Wang, Zhiliang [1 ]
Xiao, Ruoxiu [1 ,2 ]
机构
[1] Univ Sci & Technol Beijing, Sch Comp & Commun Engn, Beijing 100083, Peoples R China
[2] Univ Sci & Technol Beijing, Inst Artificial Intelligence, Beijing 100083, Peoples R China
基金
北京市自然科学基金; 中国国家自然科学基金;
关键词
COVID-19; Lesions; Computed tomography; Three-dimensional displays; Lung; Feature extraction; Image segmentation; Conditional random field; data augmentation; deep network; lung lesions segmentation; NET;
D O I
10.1109/TII.2021.3059023
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
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.
引用
收藏
页码:6528 / 6538
页数:11
相关论文
共 35 条
[1]  
Abdel-Basset M., KNOWL-BASED SYST, V215, DOI [10.1016/ j.knosys.2020, DOI 10.1016/J.KNOSYS.2020]
[2]   HSMA_WOA: A hybrid novel Slime mould algorithm with whale optimization algorithm for tackling the image segmentation problem of chest X-ray images [J].
Abdel-Basset, Mohamed ;
Chang, Victor ;
Mohamed, Reda .
APPLIED SOFT COMPUTING, 2020, 95
[3]   Correlation of Chest CT and RT-PCR Testing for Coronavirus Disease 2019 (COVID-19) in China: A Report of 1014 Cases [J].
Ai, Tao ;
Yang, Zhenlu ;
Hou, Hongyan ;
Zhan, Chenao ;
Chen, Chong ;
Lv, Wenzhi ;
Tao, Qian ;
Sun, Ziyong ;
Xia, Liming .
RADIOLOGY, 2020, 296 (02) :E32-E40
[4]  
Babiker M. S, 2020, SCHOLAR J APPL MED S, V8, P1802
[5]  
Bock S, 2018, P OSTB TH REG, P80
[6]   Pathological lung segmentation in chest CT images based on improved random walker [J].
Chen, Cheng ;
Xiao, Ruoxiu ;
Zhang, Tao ;
Lu, Yuanyuan ;
Guo, Xiaoyu ;
Wang, Jiayu ;
Chen, Hongyu ;
Wang, Zhiliang .
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2021, 200
[7]  
Chen L.C., 2017, C COMP VIS PATT REC
[8]  
Chung MS, 2020, EUR RADIOL, V30, P2182, DOI [10.1007/s00330-019-06574-1, 10.1148/radiol.2020200230]
[9]  
Cicek Ozgun, 2016, Medical Image Computing and Computer-Assisted Intervention - MICCAI 2016. 19th International Conference. Proceedings: LNCS 9901, P424, DOI 10.1007/978-3-319-46723-8_49
[10]   Ventilation/perfusion SPECT/CT findings in different lung lesions associated with COVID-19: a case series [J].
Cobes, Nina ;
Guernou, Mohamed ;
Lussato, David ;
Queneau, Mathieu ;
Songy, Bernard ;
Bonardel, Gerald ;
Grellier, Jean-Francois .
EUROPEAN JOURNAL OF NUCLEAR MEDICINE AND MOLECULAR IMAGING, 2020, 47 (10) :2453-2460