Deep Learning COVID-19 Features on CXR Using Limited Training Data Sets

Cited 493 time in webofscience Cited 421 time in scopus
  • Hit : 627
  • Download : 635
DC FieldValueLanguage
dc.contributor.authorOh, Yujinko
dc.contributor.authorPark, Sangjoonko
dc.contributor.authorYe, Jong Chulko
dc.date.accessioned2020-08-21T07:55:09Z-
dc.date.available2020-08-21T07:55:09Z-
dc.date.created2020-08-19-
dc.date.created2020-08-19-
dc.date.created2020-08-19-
dc.date.issued2020-08-
dc.identifier.citationIEEE TRANSACTIONS ON MEDICAL IMAGING, v.39, no.8, pp.2688 - 2700-
dc.identifier.issn0278-0062-
dc.identifier.urihttp://hdl.handle.net/10203/275915-
dc.description.abstractUnder the global pandemic of COVID-19, the use of artificial intelligence to analyze chest X-ray (CXR) image for COVID-19 diagnosis and patient triage is becoming important. Unfortunately, due to the emergent nature of the COVID-19 pandemic, a systematic collection of CXR data set for deep neural network training is difficult. To address this problem, here we propose a patch-based convolutional neural network approach with a relatively small number of trainable parameters for COVID-19 diagnosis. The proposed method is inspired by our statistical analysis of the potential imaging biomarkers of the CXR radiographs. Experimental results show that our method achieves state-of-the-art performance and provides clinically interpretable saliency maps, which are useful for COVID-19 diagnosis and patient triage.-
dc.languageEnglish-
dc.publisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC-
dc.titleDeep Learning COVID-19 Features on CXR Using Limited Training Data Sets-
dc.typeArticle-
dc.identifier.wosid000554893500012-
dc.identifier.scopusid2-s2.0-85087516571-
dc.type.rimsART-
dc.citation.volume39-
dc.citation.issue8-
dc.citation.beginningpage2688-
dc.citation.endingpage2700-
dc.citation.publicationnameIEEE TRANSACTIONS ON MEDICAL IMAGING-
dc.identifier.doi10.1109/TMI.2020.2993291-
dc.contributor.localauthorYe, Jong Chul-
dc.description.isOpenAccessY-
dc.type.journalArticleArticle-
dc.subject.keywordAuthorLung-
dc.subject.keywordAuthorDiseases-
dc.subject.keywordAuthorImage segmentation-
dc.subject.keywordAuthorTraining-
dc.subject.keywordAuthorNeural networks-
dc.subject.keywordAuthorSensitivity-
dc.subject.keywordAuthorComputed tomography-
dc.subject.keywordAuthorCOVID-19-
dc.subject.keywordAuthorCOVID-19-
dc.subject.keywordAuthorchest X-ray-
dc.subject.keywordAuthordeep learning-
dc.subject.keywordAuthorsegmentation-
dc.subject.keywordAuthorclassification-
dc.subject.keywordAuthorsaliency map-
dc.subject.keywordPlusCHEST RADIOGRAPHS-
dc.subject.keywordPlusCARDIOTHORACIC RATIO-
dc.subject.keywordPlusDISEASE-
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 493 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0