1. Federated deep learning for detecting COVID-19 lung abnormalities in CT: a privacy-preserving multinational validation study
- Author
-
Bernhard Kainz, Zeju Li, Heather H. C. Lee, Kevin Yu, Quande Liu, Varut Vardhanabhuti, Simon C.H. Yu, Daniel Rueckert, Pheng-Ann Heng, Tiffany Y. So, Ben Glocker, Weixin Si, Rickmer Braren, Zuxin Feng, Georgios Kaissis, Qi Dou, Egon Burian, Friederike Jungmann, Li Dong, Marcus R. Makowski, Meirui Jiang, and Commission of the European Communities
- Subjects
0301 basic medicine ,Mainland China ,Validation study ,Information privacy ,CONFIDENCE ,Coronavirus disease 2019 (COVID-19) ,Computer science ,Computer applications to medicine. Medical informatics ,MEDLINE ,R858-859.7 ,Medicine (miscellaneous) ,Health Informatics ,Article ,03 medical and health sciences ,0302 clinical medicine ,Health Information Management ,Generalizability theory ,Computed tomography ,Science & Technology ,business.industry ,Deep learning ,Diagnostic markers ,Data science ,Computer Science Applications ,030104 developmental biology ,Health Care Sciences & Services ,Multinational corporation ,Artificial intelligence ,business ,Life Sciences & Biomedicine ,030217 neurology & neurosurgery ,Medical Informatics - Abstract
Data privacy mechanisms are essential for rapidly scaling medical training databases to capture the heterogeneity of patient data distributions toward robust and generalizable machine learning systems. In the current COVID-19 pandemic, a major focus of artificial intelligence (AI) is interpreting chest CT, which can be readily used in the assessment and management of the disease. This paper demonstrates the feasibility of a federated learning method for detecting COVID-19 related CT abnormalities with external validation on patients from a multinational study. We recruited 132 patients from seven multinational different centers, with three internal hospitals from Hong Kong for training and testing, and four external, independent datasets from Mainland China and Germany, for validating model generalizability. We also conducted case studies on longitudinal scans for automated estimation of lesion burden for hospitalized COVID-19 patients. We explore the federated learning algorithms to develop a privacy-preserving AI model for COVID-19 medical image diagnosis with good generalization capability on unseen multinational datasets. Federated learning could provide an effective mechanism during pandemics to rapidly develop clinically useful AI across institutions and countries overcoming the burden of central aggregation of large amounts of sensitive data.
- Published
- 2021