tetano
Editor, Senior Moderator
Eur Radiol
. 2022 Jan 6.
doi: 10.1007/s00330-021-08334-6. Online ahead of print.
Artificial intelligence for stepwise diagnosis and monitoring of COVID-19
Hengrui Liang[SUP] #[/SUP][SUP] 1 2 [/SUP], Yuchen Guo[SUP] #[/SUP][SUP] 3 4 [/SUP], Xiangru Chen[SUP] 5 [/SUP], Keng-Leong Ang[SUP] 2 6 [/SUP], Yuwei He[SUP] 4 7 [/SUP], Na Jiang[SUP] 8 [/SUP], Qiang Du[SUP] 5 [/SUP], Qingsi Zeng[SUP] 1 9 [/SUP], Ligong Lu[SUP] 10 [/SUP], Zebin Gao[SUP] 5 [/SUP], Linduo Li[SUP] 11 [/SUP], Quanzheng Li[SUP] 12 [/SUP], Fangxing Nie[SUP] 5 [/SUP], Guiguang Ding[SUP] 3 4 7 [/SUP], Gao Huang[SUP] 5 7 [/SUP], Ailan Chen[SUP] 1 13 [/SUP], Yimin Li[SUP] 1 14 [/SUP], Weijie Guan[SUP] 1 [/SUP], Ling Sang[SUP] 1 14 [/SUP], Yuanda Xu[SUP] 1 14 [/SUP], Huai Chen[SUP] 1 9 [/SUP], Zisheng Chen[SUP] 1 [/SUP], Shiyue Li[SUP] 1 [/SUP], Nuofu Zhang[SUP] 1 [/SUP], Ying Chen[SUP] 1 [/SUP], Danxia Huang[SUP] 1 [/SUP], Run Li[SUP] 1 [/SUP], Jianfu Li[SUP] 1 2 [/SUP], Bo Cheng[SUP] 1 2 [/SUP], Yi Zhao[SUP] 1 2 [/SUP], Caichen Li[SUP] 1 2 [/SUP], Shan Xiong[SUP] 1 2 [/SUP], Runchen Wang[SUP] 1 2 [/SUP], Jun Liu[SUP] 1 2 [/SUP], Wei Wang[SUP] 1 2 [/SUP], Jun Huang[SUP] 1 2 [/SUP], Fei Cui[SUP] 1 2 [/SUP], Tao Xu[SUP] 15 [/SUP], Fleming Y M Lure[SUP] 16 [/SUP], Meixiao Zhan[SUP] 10 [/SUP], Yuanyi Huang[SUP] 17 [/SUP], Qiang Yang[SUP] 18 [/SUP], Qionghai Dai[SUP] 19 20 [/SUP], Wenhua Liang[SUP] 21 22 [/SUP], Jianxing He[SUP] 23 24 25 [/SUP], Nanshan Zhong[SUP] 1 [/SUP]
Affiliations
Abstract
Background: Main challenges for COVID-19 include the lack of a rapid diagnostic test, a suitable tool to monitor and predict a patient's clinical course and an efficient way for data sharing among multicenters. We thus developed a novel artificial intelligence system based on deep learning (DL) and federated learning (FL) for the diagnosis, monitoring, and prediction of a patient's clinical course.
Methods: CT imaging derived from 6 different multicenter cohorts were used for stepwise diagnostic algorithm to diagnose COVID-19, with or without clinical data. Patients with more than 3 consecutive CT images were trained for the monitoring algorithm. FL has been applied for decentralized refinement of independently built DL models.
Results: A total of 1,552,988 CT slices from 4804 patients were used. The model can diagnose COVID-19 based on CT alone with the AUC being 0.98 (95% CI 0.97-0.99), and outperforms the radiologist's assessment. We have also successfully tested the incorporation of the DL diagnostic model with the FL framework. Its auto-segmentation analyses co-related well with those by radiologists and achieved a high Dice's coefficient of 0.77. It can produce a predictive curve of a patient's clinical course if serial CT assessments are available.
Interpretation: The system has high consistency in diagnosing COVID-19 based on CT, with or without clinical data. Alternatively, it can be implemented on a FL platform, which would potentially encourage the data sharing in the future. It also can produce an objective predictive curve of a patient's clinical course for visualization.
Key points: • CoviDet could diagnose COVID-19 based on chest CT with high consistency; this outperformed the radiologist's assessment. Its auto-segmentation analyses co-related well with those by radiologists and could potentially monitor and predict a patient's clinical course if serial CT assessments are available. It can be integrated into the federated learning framework. • CoviDet can be used as an adjunct to aid clinicians with the CT diagnosis of COVID-19 and can potentially be used for disease monitoring; federated learning can potentially open opportunities for global collaboration.
Keywords: AI (artificial intelligence); Computer-assisted diagnosis; Coronavirus disease 2019.
. 2022 Jan 6.
doi: 10.1007/s00330-021-08334-6. Online ahead of print.
Artificial intelligence for stepwise diagnosis and monitoring of COVID-19
Hengrui Liang[SUP] #[/SUP][SUP] 1 2 [/SUP], Yuchen Guo[SUP] #[/SUP][SUP] 3 4 [/SUP], Xiangru Chen[SUP] 5 [/SUP], Keng-Leong Ang[SUP] 2 6 [/SUP], Yuwei He[SUP] 4 7 [/SUP], Na Jiang[SUP] 8 [/SUP], Qiang Du[SUP] 5 [/SUP], Qingsi Zeng[SUP] 1 9 [/SUP], Ligong Lu[SUP] 10 [/SUP], Zebin Gao[SUP] 5 [/SUP], Linduo Li[SUP] 11 [/SUP], Quanzheng Li[SUP] 12 [/SUP], Fangxing Nie[SUP] 5 [/SUP], Guiguang Ding[SUP] 3 4 7 [/SUP], Gao Huang[SUP] 5 7 [/SUP], Ailan Chen[SUP] 1 13 [/SUP], Yimin Li[SUP] 1 14 [/SUP], Weijie Guan[SUP] 1 [/SUP], Ling Sang[SUP] 1 14 [/SUP], Yuanda Xu[SUP] 1 14 [/SUP], Huai Chen[SUP] 1 9 [/SUP], Zisheng Chen[SUP] 1 [/SUP], Shiyue Li[SUP] 1 [/SUP], Nuofu Zhang[SUP] 1 [/SUP], Ying Chen[SUP] 1 [/SUP], Danxia Huang[SUP] 1 [/SUP], Run Li[SUP] 1 [/SUP], Jianfu Li[SUP] 1 2 [/SUP], Bo Cheng[SUP] 1 2 [/SUP], Yi Zhao[SUP] 1 2 [/SUP], Caichen Li[SUP] 1 2 [/SUP], Shan Xiong[SUP] 1 2 [/SUP], Runchen Wang[SUP] 1 2 [/SUP], Jun Liu[SUP] 1 2 [/SUP], Wei Wang[SUP] 1 2 [/SUP], Jun Huang[SUP] 1 2 [/SUP], Fei Cui[SUP] 1 2 [/SUP], Tao Xu[SUP] 15 [/SUP], Fleming Y M Lure[SUP] 16 [/SUP], Meixiao Zhan[SUP] 10 [/SUP], Yuanyi Huang[SUP] 17 [/SUP], Qiang Yang[SUP] 18 [/SUP], Qionghai Dai[SUP] 19 20 [/SUP], Wenhua Liang[SUP] 21 22 [/SUP], Jianxing He[SUP] 23 24 25 [/SUP], Nanshan Zhong[SUP] 1 [/SUP]
Affiliations
- PMID: 34988656
- DOI: 10.1007/s00330-021-08334-6
Abstract
Background: Main challenges for COVID-19 include the lack of a rapid diagnostic test, a suitable tool to monitor and predict a patient's clinical course and an efficient way for data sharing among multicenters. We thus developed a novel artificial intelligence system based on deep learning (DL) and federated learning (FL) for the diagnosis, monitoring, and prediction of a patient's clinical course.
Methods: CT imaging derived from 6 different multicenter cohorts were used for stepwise diagnostic algorithm to diagnose COVID-19, with or without clinical data. Patients with more than 3 consecutive CT images were trained for the monitoring algorithm. FL has been applied for decentralized refinement of independently built DL models.
Results: A total of 1,552,988 CT slices from 4804 patients were used. The model can diagnose COVID-19 based on CT alone with the AUC being 0.98 (95% CI 0.97-0.99), and outperforms the radiologist's assessment. We have also successfully tested the incorporation of the DL diagnostic model with the FL framework. Its auto-segmentation analyses co-related well with those by radiologists and achieved a high Dice's coefficient of 0.77. It can produce a predictive curve of a patient's clinical course if serial CT assessments are available.
Interpretation: The system has high consistency in diagnosing COVID-19 based on CT, with or without clinical data. Alternatively, it can be implemented on a FL platform, which would potentially encourage the data sharing in the future. It also can produce an objective predictive curve of a patient's clinical course for visualization.
Key points: • CoviDet could diagnose COVID-19 based on chest CT with high consistency; this outperformed the radiologist's assessment. Its auto-segmentation analyses co-related well with those by radiologists and could potentially monitor and predict a patient's clinical course if serial CT assessments are available. It can be integrated into the federated learning framework. • CoviDet can be used as an adjunct to aid clinicians with the CT diagnosis of COVID-19 and can potentially be used for disease monitoring; federated learning can potentially open opportunities for global collaboration.
Keywords: AI (artificial intelligence); Computer-assisted diagnosis; Coronavirus disease 2019.