Seung-Jin Yoo1, Xiaolong Qi2, Shohei Inui, Hyungjin Kim3, Yeon Joo Jeong4, Kyung Hee Lee5, Young Kyung Lee6, Bae Young Lee7, Jin Yong Kim8, Kwang Nam Jin9, Jae-Kwang Lim10, Yun-Hyeon Kim11, Ki Beom Kim12, Zicheng Jiang13, Chuxiao Shao14, Junqiang Lei15, Shengqiang Zou16, Hongqiu Pan16, Ye Gu17, Guo Zhang18, Jin Mo Goo3, Soon Ho Yoon. 1. From the Department of Radiology, Hanyang University Medical Center, Hanyang University College of Medicine, Seoul, South Korea. 2. CHESS Center, The First Hospital of Lanzhou University, Lanzhou, China. 3. Department of Radiology, Seoul National University Hospital, Seoul National College of Medicine, Seoul. 4. Department of Radiology, Pusan National University Hospital, Pusan National University School of Medicine and Biomedical Research Institute, Busan. 5. Department of Radiology, Seoul National University Bundang Hospital, Seongnam. 6. Department of Radiology, Seoul Medical Center. 7. Department of Radiology, Eunpyeong St Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul. 8. Division of Infectious Diseases, Department of Internal Medicine, Incheon Medical Center, Incheon. 9. Department of Radiology, Seoul Metropolitan Government-Seoul National University Boramae Medical Center, Seoul. 10. Department of Radiology, School of Medicine, Kyungpook National University, Daegu. 11. Department of Radiology, Chonnam National University Medical School, Gwangju. 12. Department of Radiology, Daegu Fatima Hospital, Daegu, South Korea. 13. Department of Infectious Diseases, Ankang Central Hospital, Ankang. 14. CHESS-COVID-19 Group, Lishui Central Hospital, Lishui. 15. Department of Radiology, The First Hospital of Lanzhou University, Lanzhou. 16. Department of Infectious Diseases, The Affiliated Third Hospital of Jiangsu University, Zhenjiang. 17. CHESS-COVID-19 Group, The Sixth People's Hospital of Shenyang, Shenyang. 18. CHESS-COVID-19 Group, The People's Hospital of Guangxi Zhuang Autonomous Region, Nanning, China.
Abstract
OBJECTIVE: We aimed to develop and validate the automatic quantification of coronavirus disease 2019 (COVID-19) pneumonia on computed tomography (CT) images. METHODS: This retrospective study included 176 chest CT scans of 131 COVID-19 patients from 14 Korean and Chinese institutions from January 23 to March 15, 2020. Two experienced radiologists semiautomatically drew pneumonia masks on CT images to develop the 2D U-Net for segmenting pneumonia. External validation was performed using Japanese (n = 101), Italian (n = 99), Radiopaedia (n = 9), and Chinese data sets (n = 10). The primary measures for the system's performance were correlation coefficients for extent (%) and weight (g) of pneumonia in comparison with visual CT scores or human-derived segmentation. Multivariable logistic regression analyses were performed to evaluate the association of the extent and weight with symptoms in the Japanese data set and composite outcome (respiratory failure and death) in the Spanish data set (n = 115). RESULTS: In the internal test data set, the intraclass correlation coefficients between U-Net outputs and references for the extent and weight were 0.990 and 0.993. In the Japanese data set, the Pearson correlation coefficients between U-Net outputs and visual CT scores were 0.908 and 0.899. In the other external data sets, intraclass correlation coefficients were between 0.949-0.965 (extent) and between 0.978-0.993 (weight). Extent and weight in the top quartile were independently associated with symptoms (odds ratio, 5.523 and 10.561; P = 0.041 and 0.016) and the composite outcome (odds ratio, 9.365 and 7.085; P = 0.021 and P = 0.035). CONCLUSIONS: Automatically quantified CT extent and weight of COVID-19 pneumonia were well correlated with human-derived references and independently associated with symptoms and prognosis in multinational external data sets.
OBJECTIVE: We aimed to develop and validate the automatic quantification of coronavirus disease 2019 (COVID-19) pneumonia on computed tomography (CT) images. METHODS: This retrospective study included 176 chest CT scans of 131 COVID-19 patients from 14 Korean and Chinese institutions from January 23 to March 15, 2020. Two experienced radiologists semiautomatically drew pneumonia masks on CT images to develop the 2D U-Net for segmenting pneumonia. External validation was performed using Japanese (n = 101), Italian (n = 99), Radiopaedia (n = 9), and Chinese data sets (n = 10). The primary measures for the system's performance were correlation coefficients for extent (%) and weight (g) of pneumonia in comparison with visual CT scores or human-derived segmentation. Multivariable logistic regression analyses were performed to evaluate the association of the extent and weight with symptoms in the Japanese data set and composite outcome (respiratory failure and death) in the Spanish data set (n = 115). RESULTS: In the internal test data set, the intraclass correlation coefficients between U-Net outputs and references for the extent and weight were 0.990 and 0.993. In the Japanese data set, the Pearson correlation coefficients between U-Net outputs and visual CT scores were 0.908 and 0.899. In the other external data sets, intraclass correlation coefficients were between 0.949-0.965 (extent) and between 0.978-0.993 (weight). Extent and weight in the top quartile were independently associated with symptoms (odds ratio, 5.523 and 10.561; P = 0.041 and 0.016) and the composite outcome (odds ratio, 9.365 and 7.085; P = 0.021 and P = 0.035). CONCLUSIONS: Automatically quantified CT extent and weight of COVID-19 pneumonia were well correlated with human-derived references and independently associated with symptoms and prognosis in multinational external data sets.