Can deep learning replace histopathological examinations in the differential diagnosis of cervical lymphadenopathy?

dc.contributor.authorCan, Sermin
dc.contributor.authorTurk, Omer
dc.contributor.authorAyral, Muhammed
dc.contributor.authorKozan, Gunay
dc.contributor.authorAri, Hamza
dc.contributor.authorAkdag, Mehmet
dc.contributor.authorBaylan, Muezeyyen Yildirim
dc.date.accessioned2024-04-24T16:01:53Z
dc.date.available2024-04-24T16:01:53Z
dc.date.issued2024
dc.departmentDicle Üniversitesien_US
dc.description.abstractIntroductionWe aimed to develop a diagnostic deep learning model using contrast-enhanced CT images and to investigate whether cervical lymphadenopathies can be diagnosed with these deep learning methods without radiologist interpretations and histopathological examinations.Material methodA total of 400 patients who underwent surgery for lymphadenopathy in the neck between 2010 and 2022 were retrospectively analyzed. They were examined in four groups of 100 patients: the granulomatous diseases group, the lymphoma group, the squamous cell tumor group, and the reactive hyperplasia group. The diagnoses of the patients were confirmed histopathologically. Two CT images from all the patients in each group were used in the study. The CT images were classified using ResNet50, NASNetMobile, and DenseNet121 architecture input.ResultsThe classification accuracies obtained with ResNet50, DenseNet121, and NASNetMobile were 92.5%, 90.62, and 87.5, respectively.ConclusionDeep learning is a useful diagnostic tool in diagnosing cervical lymphadenopathy. In the near future, many diseases could be diagnosed with deep learning models without radiologist interpretations and invasive examinations such as histopathological examinations. However, further studies with much larger case series are needed to develop accurate deep-learning models.en_US
dc.identifier.doi10.1007/s00405-023-08181-9
dc.identifier.endpage367en_US
dc.identifier.issn0937-4477
dc.identifier.issn1434-4726
dc.identifier.issue1en_US
dc.identifier.pmid37578497
dc.identifier.scopus2-s2.0-85167881545
dc.identifier.scopusqualityQ1
dc.identifier.startpage359en_US
dc.identifier.urihttps://doi.org/10.1007/s00405-023-08181-9
dc.identifier.urihttps://hdl.handle.net/11468/14450
dc.identifier.volume281en_US
dc.identifier.wosWOS:001048823900002
dc.identifier.wosqualityN/A
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.indekslendigikaynakPubMed
dc.language.isoenen_US
dc.publisherSpringeren_US
dc.relation.ispartofEuropean Archives of Oto-Rhino-Laryngology
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectDeep Learningen_US
dc.subjectLymphadenopathyen_US
dc.subjectGranulomatous Diseasesen_US
dc.subjectLymphomaen_US
dc.subjectSquamous Cell Tumoren_US
dc.subjectReactive Hyperplasiaen_US
dc.titleCan deep learning replace histopathological examinations in the differential diagnosis of cervical lymphadenopathy?en_US
dc.titleCan deep learning replace histopathological examinations in the differential diagnosis of cervical lymphadenopathy?
dc.typeArticleen_US

Dosyalar