Explainable COVID-19 Infections Identification and Delineation Using Calibrated Pseudo Labels

Simple item page
dc.contributor.authorLi, Ming
dc.contributor.authorFang, Yingying
dc.contributor.authorTang, Zeyu
dc.contributor.authorOnuorah, Chibudom
dc.contributor.authorXia, Jun
dc.contributor.authorSer, Javier Del
dc.contributor.authorWalsh, Simon
dc.contributor.authorYang, Guang
dc.contributor.institutionIA
dc.date.accessioned2024-09-10T13:30:02Z
dc.date.available2024-09-10T13:30:02Z
dc.date.issued2023-02-01
dc.descriptionPublisher Copyright: © 2017 IEEE.
dc.description.abstractThe upheaval brought by the arrival of the COVID-19 pandemic has continued to bring fresh challenges over the past two years. During this COVID-19 pandemic, there has been a need for rapid identification of infected patients and specific delineation of infection areas in computed tomography (CT) images. Although deep supervised learning methods have been established quickly, the scarcity of both image-level and pixel-level labels as well as the lack of explainable transparency still hinder the applicability of AI. Can we identify infected patients and delineate the infections with extreme minimal supervision? Semi-supervised learning has demonstrated promising performance under limited labelled data and sufficient unlabelled data. Inspired by semi-supervised learning, we propose a model-agnostic calibrated pseudo-labelling strategy and apply it under a consistency regularization framework to generate explainable identification and delineation results. We demonstrate the effectiveness of our model with the combination of limited labelled data and sufficient unlabelled data or weakly-labelled data. Extensive experiments have shown that our model can efficiently utilize limited labelled data and provide explainable classification and segmentation results for decision-making in clinical routine.en
dc.description.statusPeer reviewed
dc.format.extent10
dc.identifier.citationLi , M , Fang , Y , Tang , Z , Onuorah , C , Xia , J , Ser , J D , Walsh , S & Yang , G 2023 , ' Explainable COVID-19 Infections Identification and Delineation Using Calibrated Pseudo Labels ' , IEEE Transactions on Emerging Topics in Computational Intelligence , vol. 7 , no. 1 , pp. 26-35 . https://doi.org/10.1109/TETCI.2022.3189054
dc.identifier.doi10.1109/TETCI.2022.3189054
dc.identifier.issn2471-285X
dc.identifier.urihttps://hdl.handle.net/11556/5087
dc.identifier.urlhttp://www.scopus.com/inward/record.url?scp=85135212193&partnerID=8YFLogxK
dc.language.isoeng
dc.relation.ispartofIEEE Transactions on Emerging Topics in Computational Intelligence
dc.relation.projectIDHorizon 2020 Framework Programme, H2020, 952172
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subject.keywordsCOVID-19
dc.subject.keywordsconsistency regularization
dc.subject.keywordsexplainability
dc.subject.keywordspseudo-labelling
dc.subject.keywordssemi-supervised learning
dc.subject.keywordsComputer Science Applications
dc.subject.keywordsControl and Optimization
dc.subject.keywordsComputational Mathematics
dc.subject.keywordsArtificial Intelligence
dc.titleExplainable COVID-19 Infections Identification and Delineation Using Calibrated Pseudo Labelsen
dc.typejournal article
Files