Classification of Different Tympanic Membrane Conditions Using Fused Deep Hypercolumn Features and Bidirectional LSTM

Basit Öğe Kaydı
dc.authoridUCAR, EMINE/0000-0002-6838-3015
dc.authoridAKYOL, KEMAL/0000-0002-2272-5243
dc.authoridUCAR, Murat/0000-0001-9997-4267
dc.authoridATILA, UMIT/0000-0002-1576-9977
dc.contributor.authorUcar, M.
dc.contributor.authorAkyol, K.
dc.contributor.authorAtila, U.
dc.contributor.authorUcar, E.
dc.date.accessioned2024-09-29T15:57:23Z
dc.date.available2024-09-29T15:57:23Z
dc.date.issued2022
dc.departmentKarabük Üniversitesien_US
dc.description.abstractObjectives: Middle ear inflammatory diseases are global health problem that can have serious consequences such as hearing loss and speech disorders. The high cost of medical devices such as otoendoscope and oto-microscope used by the specialists for the diagnosis of the disease prevents its widespread use. In addition, the decisions of otolaryngologists may differ due to the subjective visual examinations. For this reason, computer-aided middle ear disease diagnosis systems are needed to eliminate subjective diagnosis and high cost problems. To this aim, a hybrid deep learning approach was proposed for automatic recognition of different tympanic membrane conditions such as earwax plug, myringosclerosis, chronic otitis media and normal from the otoscopy images. Materials and methods: In this study we used public Ear Imagery dataset containing 880 otoscopy images. The proposed approach detects keypoints from the otoscopy images and following the obtained keypoint positions, extracts hypercolumn deep features from 5 different layers of the VGG 16 model. Classification of tympanic membrane conditions were realized by feeding the deep hypercolumn features to Bi-LSTM network in the form of non-time related data. Results: The performance of the proposed model was evaluated in three different color spaces as RedGreen-Blue (RGB), Hue-Saturation-Value (HSV) and Haematoxylin-Eosin-Diaminobenzidine (HED). The proposed model achieved acceptable results in all color spaces, moreover it showed a very successful performance in classifying tympanic membrane conditions especially in RGB space. Experimental studies showed that the proposed model achieved Acc of 99.06%, Sen of 98.13% and Spe of 99.38%. Conclusion: As a result, a robust model with high sensitivity was obtained for classification of tympanic membrane conditions and it was shown that Bi-LSTM network, which is generally used with time-related data, could also be used successfully with non-time related data for diagnosis of tympanic membrane conditions.(C) 2021 AGBM. Published by Elsevier Masson SAS. All rights reserved.en_US
dc.identifier.doi10.1016/j.irbm.2021.01.001
dc.identifier.endpage197en_US
dc.identifier.issn1959-0318
dc.identifier.issn1876-0988
dc.identifier.issue3en_US
dc.identifier.scopus2-s2.0-85100027325en_US
dc.identifier.scopusqualityQ2en_US
dc.identifier.startpage187en_US
dc.identifier.urihttps://doi.org/10.1016/j.irbm.2021.01.001
dc.identifier.urihttps://hdl.handle.net/20.500.14619/4783
dc.identifier.volume43en_US
dc.identifier.wosWOS:000809732400005en_US
dc.identifier.wosqualityQ2en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherElsevier Science Incen_US
dc.relation.ispartofIrbmen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectTympanic membraneen_US
dc.subjectBidirectional LSTMen_US
dc.subjectDeep learningen_US
dc.subjectHypercolumn featuresen_US
dc.subjectKeypoint detectionen_US
dc.titleClassification of Different Tympanic Membrane Conditions Using Fused Deep Hypercolumn Features and Bidirectional LSTMen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu