A deep-learning-based framework for severity assessment of COVID-19 with CT images

doi:10.1016/j.eswa.2021.115616

	A deep-learning-based framework for severity assessment of COVID-19 with CT images
	Li, Zhidan 1; Zhao, Shixuan 1; Chen, Yang 2; Luo, Fuya 1; Kang, Zhiqing 1; Cai, Shengping 3; Zhao, Wei 4; Liu, Jun 4; Zhao, Di 5; Li, Yongjie 1
	2021-12-15
发表期刊	EXPERT SYSTEMS WITH APPLICATIONS
ISSN	0957-4174
卷号	185 页码:11
摘要	Millions of positive COVID-19 patients are suffering from the pandemic around the world, a critical step in the management and treatment is severity assessment, which is quite challenging with the limited medical resources. Currently, several artificial intelligence systems have been developed for the severity assessment. However, imprecise severity assessment and insufficient data are still obstacles. To address these issues, we proposed a novel deep-learning-based framework for the fine-grained severity assessment using 3D CT scans, by jointly performing lung segmentation and lesion segmentation. The main innovations in the proposed framework include: 1) decomposing 3D CT scan into multi-view slices for reducing the complexity of 3D model, 2) integrating prior knowledge (dual-Siamese channels and clinical metadata) into our model for improving the model performance. We evaluated the proposed method on 1301 CT scans of 449 COVID-19 cases collected by us, our method achieved an accuracy of 86.7% for four-way classification, with the sensitivities of 92%, 78%, 95%, 89% for four stages. Moreover, ablation study demonstrated the effectiveness of the major components in our model. This indicates that our method may contribute a potential solution to severity assessment of COVID-19 patients using CT images and clinical metadata.
关键词	COVID-19 Deep learning Severity assessment Multi-view lesion Dual-Siamese channels Clinical metadata
DOI	10.1016/j.eswa.2021.115616
收录类别	SCI
语种	英语
资助项目	Key Area R&D Program of Guangdong Province[2018B030338001]
WOS研究方向	Computer Science ; Engineering ; Operations Research & Management Science
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic ; Operations Research & Management Science
WOS记录号	WOS:000705440000003
出版者	PERGAMON-ELSEVIER SCIENCE LTD
引用统计	被引频次：28[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/16941
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Chen, Yang; Li, Yongjie
作者单位	1.Univ Elect Sci & Technol China, MOE Key Lab Neuroinformat, Chengdu, Peoples R China 2.Sichuan Univ, West China Hosp, West China Biomed Big Data Ctr, Chengdu, Peoples R China 3.Wuhan Red Cross Hosp, Dept Radiol, Wuhan, Peoples R China 4.Cent South Univ, Second Xiangya Hosp, Dept Radiol, Changsha, Peoples R China 5.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Li, Zhidan,Zhao, Shixuan,Chen, Yang,et al. A deep-learning-based framework for severity assessment of COVID-19 with CT images[J]. EXPERT SYSTEMS WITH APPLICATIONS,2021,185:11.
APA	Li, Zhidan.,Zhao, Shixuan.,Chen, Yang.,Luo, Fuya.,Kang, Zhiqing.,...&Li, Yongjie.(2021).A deep-learning-based framework for severity assessment of COVID-19 with CT images.EXPERT SYSTEMS WITH APPLICATIONS,185,11.
MLA	Li, Zhidan,et al."A deep-learning-based framework for severity assessment of COVID-19 with CT images".EXPERT SYSTEMS WITH APPLICATIONS 185(2021):11.