File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Federated deep learning for detecting COVID-19 lung abnormalities in CT: a privacy-preserving multinational validation study

TitleFederated deep learning for detecting COVID-19 lung abnormalities in CT: a privacy-preserving multinational validation study
Authors
Issue Date2021
PublisherNature Publishing Group: Open Access Journals. The Journal's web site is located at https://www.nature.com/npjdigitalmed/
Citation
npj Digital Medicine, 2021, v. 4 n. 1, p. article no. 60 How to Cite?
AbstractData 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.
Persistent Identifierhttp://hdl.handle.net/10722/299358
ISSN
2023 Impact Factor: 12.4
2023 SCImago Journal Rankings: 4.273
PubMed Central ID
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorDou, Q-
dc.contributor.authorSo, TY-
dc.contributor.authorJiang, M-
dc.contributor.authorLiu, Q-
dc.contributor.authorVardhanabhuti, V-
dc.contributor.authorKaissis, G-
dc.contributor.authorLi, Z-
dc.contributor.authorSi, W-
dc.contributor.authorLee, HHC-
dc.contributor.authorYu, K-
dc.contributor.authorFeng, Z-
dc.contributor.authorDong, L-
dc.contributor.authorBurian, E-
dc.contributor.authorJungmann, F-
dc.contributor.authorBraren, R-
dc.contributor.authorMakowski, M-
dc.contributor.authorKainz, B-
dc.contributor.authorRueckert, D-
dc.contributor.authorGlocker, B-
dc.contributor.authorYu, SCH-
dc.contributor.authorHeng, PA-
dc.date.accessioned2021-05-10T07:00:39Z-
dc.date.available2021-05-10T07:00:39Z-
dc.date.issued2021-
dc.identifier.citationnpj Digital Medicine, 2021, v. 4 n. 1, p. article no. 60-
dc.identifier.issn2398-6352-
dc.identifier.urihttp://hdl.handle.net/10722/299358-
dc.description.abstractData 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.-
dc.languageeng-
dc.publisherNature Publishing Group: Open Access Journals. The Journal's web site is located at https://www.nature.com/npjdigitalmed/-
dc.relation.ispartofnpj Digital Medicine-
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.-
dc.titleFederated deep learning for detecting COVID-19 lung abnormalities in CT: a privacy-preserving multinational validation study-
dc.typeArticle-
dc.identifier.emailVardhanabhuti, V: varv@hku.hk-
dc.identifier.authorityVardhanabhuti, V=rp01900-
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.1038/s41746-021-00431-6-
dc.identifier.pmid33782526-
dc.identifier.pmcidPMC8007806-
dc.identifier.scopuseid_2-s2.0-85103580182-
dc.identifier.hkuros322350-
dc.identifier.volume4-
dc.identifier.issue1-
dc.identifier.spagearticle no. 60-
dc.identifier.epagearticle no. 60-
dc.identifier.isiWOS:000634819200001-
dc.publisher.placeUnited Kingdom-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats