Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.13091/3658
Full metadata record
DC FieldValueLanguage
dc.contributor.authorÖrnek, Ahmet Haydar-
dc.contributor.authorCeylan, Murat-
dc.date.accessioned2023-03-03T13:32:23Z-
dc.date.available2023-03-03T13:32:23Z-
dc.date.issued2023-
dc.identifier.issn1768-6733-
dc.identifier.issn2116-7176-
dc.identifier.urihttps://doi.org/10.1080/17686733.2023.2167459-
dc.identifier.urihttps://hdl.handle.net/20.500.13091/3658-
dc.descriptionArticle; Early Accessen_US
dc.description.abstractEarly diagnosis systems have vital importance to monitor and follow-up the conditions of neonates. Thermal imaging as a non-invasive and non-contact method has been used to monitor neonates for over decades. In this study, we train a convolutional neural network (CNN) model that classifies medical thermograms as healthy and unhealthy using real neonatal thermal images captured within a year from the Neonatal Intensive Care Unit (NICU), Faculty of Medicine at Selcuk University, Turkey. The trained model achieved 99.91% accuracy for train, 99.47% accuracy for validation, and 99.82% accuracy for test data. The test data were never used during training. Although the trained model achieves over 99% accuracy, how it works was not known because of the CNNs' Black-Box nature. The four visual Explainable Artificial Intelligence methods that are GradCAM, GradCAM++, LayerCAM, and EigenCAM and a new ensemble visual explanation method named CodCAM are used to visualise the important parts of the neonatal thermal images for classification. Therefore, medical specialists are going to know which regions of the thermograms (i.e. parts of the neonates) affect the trained CNN's decision so as to build trust in AI models and evaluate the results.en_US
dc.description.sponsorshipTurkiye Bilimsel ve Teknolojik Arastirma Kurumu [215E019]en_US
dc.description.sponsorshipThe work was supported by the Turkiye Bilimsel ve Teknolojik Arastirma Kurumu [215E019].en_US
dc.language.isoenen_US
dc.publisherTaylor & Francis Ltden_US
dc.relation.ispartofQuantitative Infrared Thermography Journalen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectClass activation mappingen_US
dc.subjectdeep learningen_US
dc.subjectexplainable artificial intelligenceen_US
dc.subjecthealthcareen_US
dc.subjectmedicineen_US
dc.subjectneonateen_US
dc.subjectInfrared Thermographyen_US
dc.subjectNeural-Networksen_US
dc.subjectSystemen_US
dc.titleCodCAM: A new ensemble visual explanation for classification of medical thermal imagesen_US
dc.typeArticleen_US
dc.identifier.doi10.1080/17686733.2023.2167459-
dc.identifier.scopus2-s2.0-85147262610en_US
dc.departmentKTÜNen_US
dc.identifier.wosWOS:000920967400001en_US
dc.institutionauthor-
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanen_US
dc.authorscopusid57210593918-
dc.authorscopusid56276648900-
dc.identifier.scopusqualityQ3-
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.fulltextWith Fulltext-
item.languageiso639-1en-
item.openairetypeArticle-
item.grantfulltextembargo_20300101-
item.cerifentitytypePublications-
crisitem.author.dept02.04. Department of Electrical and Electronics Engineering-
Appears in Collections:Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collections
WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collections
Files in This Item:
File SizeFormat 
CodCAM A new ensemble visual explanation for classification of medical thermal images.pdf
  Until 2030-01-01
15.08 MBAdobe PDFView/Open    Request a copy
Show simple item record



CORE Recommender

WEB OF SCIENCETM
Citations

4
checked on May 18, 2024

Page view(s)

120
checked on May 20, 2024

Download(s)

4
checked on May 20, 2024

Google ScholarTM

Check




Altmetric


Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.