Diagnosis of COVID-19 Pneumonia Based on Graph Convolutional Network
A three-dimensional (3D) deep learning method is proposed, which enables the rapid diagnosis of coronavirus disease 2019 (COVID-19) and thus significantly reduces the burden on radiologists and physicians. Inspired by the fact that the current chest computed tomography (CT) datasets are diversified...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-01-01
|
| Series: | Frontiers in Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmed.2020.612962/full |
| _version_ | 1818676760996216832 |
|---|---|
| author | Xiaoling Liang Xiaoling Liang Yuexin Zhang Jiahong Wang Qing Ye Qing Ye Yanhong Liu Jinwu Tong |
| author_facet | Xiaoling Liang Xiaoling Liang Yuexin Zhang Jiahong Wang Qing Ye Qing Ye Yanhong Liu Jinwu Tong |
| author_sort | Xiaoling Liang |
| collection | DOAJ |
| description | A three-dimensional (3D) deep learning method is proposed, which enables the rapid diagnosis of coronavirus disease 2019 (COVID-19) and thus significantly reduces the burden on radiologists and physicians. Inspired by the fact that the current chest computed tomography (CT) datasets are diversified in equipment types, we propose a COVID-19 graph in a graph convolutional network (GCN) to incorporate multiple datasets that differentiate the COVID-19 infected cases from normal controls. Specifically, we first apply a 3D convolutional neural network (3D-CNN) to extract image features from the initial 3D-CT images. In this part, a transfer learning method is proposed to improve the performance, which uses the task of predicting equipment type to initialize the parameters of the 3D-CNN structure. Second, we design a COVID-19 graph in GCN based on the extracted features. The graph divides all samples into several clusters, and samples with the same equipment type compose a cluster. Then we establish edge connections between samples in the same cluster. To compute accurate edge weights, we propose to combine the correlation distance of the extracted features and the score differences of subjects from the 3D-CNN structure. Lastly, by inputting the COVID-19 graph into GCN, we obtain the final diagnosis results. In experiments, the dataset contains 399 COVID-19 infected cases, and 400 normal controls from six equipment types. Experimental results show that the accuracy, sensitivity, and specificity of our method reach 98.5%, 99.9%, and 97%, respectively. |
| first_indexed | 2024-12-17T08:48:36Z |
| format | Article |
| id | doaj.art-57e1314ca2da402c897c62210299fc1e |
| institution | Directory Open Access Journal |
| issn | 2296-858X |
| language | English |
| last_indexed | 2024-12-17T08:48:36Z |
| publishDate | 2021-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Medicine |
| spelling | doaj.art-57e1314ca2da402c897c62210299fc1e2022-12-21T21:56:08ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2021-01-01710.3389/fmed.2020.612962612962Diagnosis of COVID-19 Pneumonia Based on Graph Convolutional NetworkXiaoling Liang0Xiaoling Liang1Yuexin Zhang2Jiahong Wang3Qing Ye4Qing Ye5Yanhong Liu6Jinwu Tong7Department of Marine Engineering, Dalian Maritime University, Dalian, ChinaDepartment of Electrical and Computer Engineering, National University of Singapore, Singapore, SingaporeSchool of Instrument Science and Engineering, Southeast University, Nanjing, ChinaDepartment of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign, Champaign, IL, United StatesDivision of Life Sciences and Medicine, Department of Pathology, The First Affiliated Hospital of USTC, University of Science and Technology of China, Hefei, ChinaDivision of Life Sciences and Medicine, Intelligent Pathology Institute, University of Science and Technology of China, Hefei, ChinaDepartment of Pathology, Nanjing Drum Tower Hospital, The Affiliated Hospital of Nanjing University Medical School, Nanjing, ChinaSchool of Innovation and Entrepreneurship, Nanjing Institute of Technology, Nanjing, ChinaA three-dimensional (3D) deep learning method is proposed, which enables the rapid diagnosis of coronavirus disease 2019 (COVID-19) and thus significantly reduces the burden on radiologists and physicians. Inspired by the fact that the current chest computed tomography (CT) datasets are diversified in equipment types, we propose a COVID-19 graph in a graph convolutional network (GCN) to incorporate multiple datasets that differentiate the COVID-19 infected cases from normal controls. Specifically, we first apply a 3D convolutional neural network (3D-CNN) to extract image features from the initial 3D-CT images. In this part, a transfer learning method is proposed to improve the performance, which uses the task of predicting equipment type to initialize the parameters of the 3D-CNN structure. Second, we design a COVID-19 graph in GCN based on the extracted features. The graph divides all samples into several clusters, and samples with the same equipment type compose a cluster. Then we establish edge connections between samples in the same cluster. To compute accurate edge weights, we propose to combine the correlation distance of the extracted features and the score differences of subjects from the 3D-CNN structure. Lastly, by inputting the COVID-19 graph into GCN, we obtain the final diagnosis results. In experiments, the dataset contains 399 COVID-19 infected cases, and 400 normal controls from six equipment types. Experimental results show that the accuracy, sensitivity, and specificity of our method reach 98.5%, 99.9%, and 97%, respectively.https://www.frontiersin.org/articles/10.3389/fmed.2020.612962/fullCOVID-19graph convolutional network3D convolutional neural networkequipment typeschest computed tomography |
| spellingShingle | Xiaoling Liang Xiaoling Liang Yuexin Zhang Jiahong Wang Qing Ye Qing Ye Yanhong Liu Jinwu Tong Diagnosis of COVID-19 Pneumonia Based on Graph Convolutional Network Frontiers in Medicine COVID-19 graph convolutional network 3D convolutional neural network equipment types chest computed tomography |
| title | Diagnosis of COVID-19 Pneumonia Based on Graph Convolutional Network |
| title_full | Diagnosis of COVID-19 Pneumonia Based on Graph Convolutional Network |
| title_fullStr | Diagnosis of COVID-19 Pneumonia Based on Graph Convolutional Network |
| title_full_unstemmed | Diagnosis of COVID-19 Pneumonia Based on Graph Convolutional Network |
| title_short | Diagnosis of COVID-19 Pneumonia Based on Graph Convolutional Network |
| title_sort | diagnosis of covid 19 pneumonia based on graph convolutional network |
| topic | COVID-19 graph convolutional network 3D convolutional neural network equipment types chest computed tomography |
| url | https://www.frontiersin.org/articles/10.3389/fmed.2020.612962/full |
| work_keys_str_mv | AT xiaolingliang diagnosisofcovid19pneumoniabasedongraphconvolutionalnetwork AT xiaolingliang diagnosisofcovid19pneumoniabasedongraphconvolutionalnetwork AT yuexinzhang diagnosisofcovid19pneumoniabasedongraphconvolutionalnetwork AT jiahongwang diagnosisofcovid19pneumoniabasedongraphconvolutionalnetwork AT qingye diagnosisofcovid19pneumoniabasedongraphconvolutionalnetwork AT qingye diagnosisofcovid19pneumoniabasedongraphconvolutionalnetwork AT yanhongliu diagnosisofcovid19pneumoniabasedongraphconvolutionalnetwork AT jinwutong diagnosisofcovid19pneumoniabasedongraphconvolutionalnetwork |