Mix Contrast for COVID-19 Mild-to-Critical Prediction | |
Zhu, Yongbei7,8,9; Wang, Shuo7,8,9; Wang, Siwen4; Wu, Qingxia6; Wang, Liusu7,8,9; Li, Hongjun5; Wang, Meiyun2,3; Niu, Meng1; Zha, Yunfei10,11; Tian, Jie7,8,9 | |
刊名 | IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING |
2021-12-01 | |
卷号 | 68期号:12页码:3725-3736 |
关键词 | COVID-19 Computed tomography Measurement Hospitals Loss measurement Training Task analysis Coronavirus disease 2019 (COVID-19) contrastive learning computed tomography mixup prognosis |
ISSN号 | 0018-9294 |
DOI | 10.1109/TBME.2021.3085576 |
通讯作者 | Tian, Jie(tian@ieee.org) |
英文摘要 | Objective: In a few patients with mild COVID-19, there is a possibility of the infection becoming severe or critical in the future. This work aims to identify high-risk patients who have a high probability of changing from mild to critical COVID-19 (only account for 5% of cases). Methods: Using traditional convolutional neural networks for classification may not be suitable to identify this 5% of high risk patients from an entire dataset due to the highly imbalanced label distribution. To address this problem, we propose a Mix Contrast model, which matches original features with mixed features for contrastive learning. Three modules are proposed for training the model: 1) a cumulative learning strategy for synthesizing the mixed feature; 2) a commutative feature combination module for learning the commutative law of feature concatenation; 3) a united pairwise loss assigning adaptive weights for sample pairs with different class anchors based on their current optimization status. Results: We collect a multi-center computed tomography dataset including 918 confirmed COVID-19 patients from four hospitals and evaluate the proposed method on both the COVID-19 mild-to-critical prediction and COVID-19 diagnosis tasks. For mild-to-critical prediction, the experimental results show a recall of 0.80 and a specificity of 0.815. For diagnosis, the model shows comparable results with deep neural networks using a large dataset. Our method demonstrates improvements when the amount of training data is small or imbalanced. Significance: Identifying mild-to-critical COVID-19 patients is important for early prevention and personalized treatment planning. |
资助项目 | Ministry of Science and Technology of China[2017YFA0205200] ; National Natural Science Foundation of China[82001913] ; National Natural Science Foundation of China[82001914] ; China Postdoctoral Science Foundation[2019TQ0019] ; China Postdoctoral Science Foundation[2020M670101] |
WOS关键词 | LUNG |
WOS研究方向 | Engineering |
语种 | 英语 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
WOS记录号 | WOS:000720518600030 |
资助机构 | Ministry of Science and Technology of China ; National Natural Science Foundation of China ; China Postdoctoral Science Foundation |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/46452] |
专题 | 自动化研究所_中国科学院分子影像重点实验室 |
通讯作者 | Tian, Jie |
作者单位 | 1.China Med Univ, Dept Intervent Radiol, Hosp 1, Shenyang, Peoples R China 2.Zhengzhou Univ, Peoples Hosp, Zhengzhou, Peoples R China 3.Zhengzhou Univ, Henan Prov Peoples Hosp, Dept Med Imaging, Zhengzhou, Peoples R China 4.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 5.Capital Med Univ, Beijing Youan Hosp, Dept Radiol, Beijing, Peoples R China 6.Northeastern Univ, Coll Med & Biomed Informat Engn, Shenyang, Peoples R China 7.Beijing Key Lab Mol Imaging, Beijing 100190, Peoples R China 8.Inst Automat, CAS Key Lab Mol Imaging, Beijing 100190, Peoples R China 9.Beihang Univ, Beijing Adv Innovat Ctr Big Data Based Precis Med, Sch Med & Engn, Beijing 100191, Peoples R China 10.Wuhan Univ, Renmin Hosp, Dept Infect Prevent & Control Off, Wuhan, Peoples R China |
推荐引用方式 GB/T 7714 | Zhu, Yongbei,Wang, Shuo,Wang, Siwen,et al. Mix Contrast for COVID-19 Mild-to-Critical Prediction[J]. IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING,2021,68(12):3725-3736. |
APA | Zhu, Yongbei.,Wang, Shuo.,Wang, Siwen.,Wu, Qingxia.,Wang, Liusu.,...&Tian, Jie.(2021).Mix Contrast for COVID-19 Mild-to-Critical Prediction.IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING,68(12),3725-3736. |
MLA | Zhu, Yongbei,et al."Mix Contrast for COVID-19 Mild-to-Critical Prediction".IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING 68.12(2021):3725-3736. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论