Assisting scalable diagnosis automatically via CT images in the combat against COVID-19
| Autor: | Qin Zhong, Zhibing Zhang, Yuhui Sun, Xia Fu, Lei Zhang, Weipeng Fan, Xixiang Lin, Wei Shan, Gao Huang, J Du, Yanqing Fan, Lin Xu, Gang Guo, Yaou Liu, Chenghui Zhao, Na Zhang, Bohan Liu, Zongren Li, Guo Huayuan, Peifang Zhang, Rongpin Wang, Lin Ma, Zhenhua Zhao, Liuquan Cheng, Kunlun He, Haipeng Shen, Weimin An, Meifang Li, Jia Qian, Jicheng Du, Hao Li, Xuelong Hu, Lutao Dai, Peng Xie, Yan-Lin Yang, Xizhou Guan, Lin Li, Yiqing Tan, Jianxin Zhou, Yongkang Nie, Chongchong Wu, Liu Minchao, Wenjun Wang, Ning Xing, Pan Liu |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
China
medicine.medical_specialty Coronavirus disease 2019 (COVID-19) Science Computed tomography 030204 cardiovascular system & hematology Sensitivity and Specificity Article 03 medical and health sciences Deep Learning 0302 clinical medicine Medical imaging Humans Medicine 030212 general & internal medicine Lung Retrospective Studies Multidisciplinary Case detection medicine.diagnostic_test SARS-CoV-2 business.industry COVID-19 Retrospective cohort study Pneumonia medicine.disease Computer science Data Accuracy Viral infection Radiology Tomography X-Ray Computed business Case identification Loss of life |
| Zdroj: | Scientific Reports, Vol 11, Iss 1, Pp 1-8 (2021) Scientific Reports |
| ISSN: | 2045-2322 |
| Popis: | The pandemic of Coronavirus Disease 2019 (COVID-19) is causing enormous loss of life globally. Prompt case identification is critical. The reference method is the real-time reverse transcription PCR (RT-PCR) assay, whose limitations may curb its prompt large-scale application. COVID-19 manifests with chest computed tomography (CT) abnormalities, some even before the onset of symptoms. We tested the hypothesis that the application of deep learning (DL) to 3D CT images could help identify COVID-19 infections. Using data from 920 COVID-19 and 1,073 non-COVID-19 pneumonia patients, we developed a modified DenseNet-264 model, COVIDNet, to classify CT images to either class. When tested on an independent set of 233 COVID-19 and 289 non-COVID-19 pneumonia patients, COVIDNet achieved an accuracy rate of 94.3% and an area under the curve of 0.98. As of March 23, 2020, the COVIDNet system had been used 11,966 times with a sensitivity of 91.12% and a specificity of 88.50% in six hospitals with PCR confirmation. Application of DL to CT images may improve both efficiency and capacity of case detection and long-term surveillance. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|