TY - JOUR
T1 - Hypergraph learning for identification of COVID-19 with CT imaging
AU - Di, Donglin
AU - Shi, Feng
AU - Yan, Fuhua
AU - Xia, Liming
AU - Mo, Zhanhao
AU - Ding, Zhongxiang
AU - Shan, Fei
AU - Song, Bin
AU - Li, Shengrui
AU - Wei, Ying
AU - Shao, Ying
AU - Han, Miaofei
AU - Gao, Yaozong
AU - Sui, He
AU - Gao, Yue
AU - Shen, Dinggang
N1 - Funding Information:
This work was supported in part by the National Natural Science Funds of China ( 61671267 , 81871337 ), Beijing Natural Science Foundation ( 4182022 ), National Key Research and Development Program of China ( 2018YFC0116400 ), Wuhan Science and technology program (Grant no. 2018060401011326 ), Hubei Provincial Novel Pneumonia Emergency Science and Technology Project (2020FCA021), Huazhong University of Science and Technology Novel Coronavirus Pneumonia Emergency Science and Technology Project (2020kfyXGYJ014 ).
Publisher Copyright:
© 2020 Elsevier B.V.
PY - 2021/2
Y1 - 2021/2
N2 - The coronavirus disease, named COVID-19, has become the largest global public health crisis since it started in early 2020. CT imaging has been used as a complementary tool to assist early screening, especially for the rapid identification of COVID-19 cases from community acquired pneumonia (CAP) cases. The main challenge in early screening is how to model the confusing cases in the COVID-19 and CAP groups, with very similar clinical manifestations and imaging features. To tackle this challenge, we propose an Uncertainty Vertex-weighted Hypergraph Learning (UVHL) method to identify COVID-19 from CAP using CT images. In particular, multiple types of features (including regional features and radiomics features) are first extracted from CT image for each case. Then, the relationship among different cases is formulated by a hypergraph structure, with each case represented as a vertex in the hypergraph. The uncertainty of each vertex is further computed with an uncertainty score measurement and used as a weight in the hypergraph. Finally, a learning process of the vertex-weighted hypergraph is used to predict whether a new testing case belongs to COVID-19 or not. Experiments on a large multi-center pneumonia dataset, consisting of 2148 COVID-19 cases and 1182 CAP cases from five hospitals, are conducted to evaluate the prediction accuracy of the proposed method. Results demonstrate the effectiveness and robustness of our proposed method on the identification of COVID-19 in comparison to state-of-the-art methods.
AB - The coronavirus disease, named COVID-19, has become the largest global public health crisis since it started in early 2020. CT imaging has been used as a complementary tool to assist early screening, especially for the rapid identification of COVID-19 cases from community acquired pneumonia (CAP) cases. The main challenge in early screening is how to model the confusing cases in the COVID-19 and CAP groups, with very similar clinical manifestations and imaging features. To tackle this challenge, we propose an Uncertainty Vertex-weighted Hypergraph Learning (UVHL) method to identify COVID-19 from CAP using CT images. In particular, multiple types of features (including regional features and radiomics features) are first extracted from CT image for each case. Then, the relationship among different cases is formulated by a hypergraph structure, with each case represented as a vertex in the hypergraph. The uncertainty of each vertex is further computed with an uncertainty score measurement and used as a weight in the hypergraph. Finally, a learning process of the vertex-weighted hypergraph is used to predict whether a new testing case belongs to COVID-19 or not. Experiments on a large multi-center pneumonia dataset, consisting of 2148 COVID-19 cases and 1182 CAP cases from five hospitals, are conducted to evaluate the prediction accuracy of the proposed method. Results demonstrate the effectiveness and robustness of our proposed method on the identification of COVID-19 in comparison to state-of-the-art methods.
KW - COVID-19 pneumonia
KW - Hypergraph learning
KW - Uncertainty calculation
KW - Vertex-weighted
UR - http://www.scopus.com/inward/record.url?scp=85097331487&partnerID=8YFLogxK
U2 - 10.1016/j.media.2020.101910
DO - 10.1016/j.media.2020.101910
M3 - Article
C2 - 33285483
AN - SCOPUS:85097331487
VL - 68
JO - Medical Image Analysis
JF - Medical Image Analysis
SN - 1361-8415
M1 - 101910
ER -