TY - JOUR
T1 - A novel multiple instance learning framework for COVID-19 severity assessment via data augmentation and self-supervised learning
AU - Li, Zekun
AU - Zhao, Wei
AU - Shi, Feng
AU - Qi, Lei
AU - Xie, Xingzhi
AU - Wei, Ying
AU - Ding, Zhongxiang
AU - Gao, Yang
AU - Wu, Shangjie
AU - Shi, Yinghuan
AU - Shen, Dinggang
AU - Liu, Jun
N1 - Funding Information:
The work was supported by the National Key Research and Development Program of China (2019YFC0118300), National Natural Science Foundation of China (61673203, 81927808). The work was also supported by the Key Emergency Project of Pneumonia Epidemic of novel coronavirus infection (2020SK3006), Emergency Project of Prevention and Control for COVID-19 of Central South University (160260005) and Foundation from Changsha Scientific and Technical Bureau, China (kq2001001).
Publisher Copyright:
© 2021
PY - 2021/4
Y1 - 2021/4
N2 - How to fast and accurately assess the severity level of COVID-19 is an essential problem, when millions of people are suffering from the pandemic around the world. Currently, the chest CT is regarded as a popular and informative imaging tool for COVID-19 diagnosis. However, we observe that there are two issues – weak annotation and insufficient data that may obstruct automatic COVID-19 severity assessment with CT images. To address these challenges, we propose a novel three-component method, i.e., 1) a deep multiple instance learning component with instance-level attention to jointly classify the bag and also weigh the instances, 2) a bag-level data augmentation component to generate virtual bags by reorganizing high confidential instances, and 3) a self-supervised pretext component to aid the learning process. We have systematically evaluated our method on the CT images of 229 COVID-19 cases, including 50 severe and 179 non-severe cases. Our method could obtain an average accuracy of 95.8%, with 93.6% sensitivity and 96.4% specificity, which outperformed previous works.
AB - How to fast and accurately assess the severity level of COVID-19 is an essential problem, when millions of people are suffering from the pandemic around the world. Currently, the chest CT is regarded as a popular and informative imaging tool for COVID-19 diagnosis. However, we observe that there are two issues – weak annotation and insufficient data that may obstruct automatic COVID-19 severity assessment with CT images. To address these challenges, we propose a novel three-component method, i.e., 1) a deep multiple instance learning component with instance-level attention to jointly classify the bag and also weigh the instances, 2) a bag-level data augmentation component to generate virtual bags by reorganizing high confidential instances, and 3) a self-supervised pretext component to aid the learning process. We have systematically evaluated our method on the CT images of 229 COVID-19 cases, including 50 severe and 179 non-severe cases. Our method could obtain an average accuracy of 95.8%, with 93.6% sensitivity and 96.4% specificity, which outperformed previous works.
KW - COVID-19
KW - Chest CT
KW - Data augmentation
KW - Multiple instance learning
KW - Self-supervised learning
UR - http://www.scopus.com/inward/record.url?scp=85100692794&partnerID=8YFLogxK
U2 - 10.1016/j.media.2021.101978
DO - 10.1016/j.media.2021.101978
M3 - Article
C2 - 33588121
AN - SCOPUS:85100692794
SN - 1361-8415
VL - 69
JO - Medical Image Analysis
JF - Medical Image Analysis
M1 - 101978
ER -