Deep convolutional neural networks for onychomycosis detection using microscopic images with KOH examination

Basit Öğe Kaydı
dc.authoridGülsüm Gençoğlan / 0000-0002-0650-0722en_US
dc.authorscopusidGülsüm Gençoğlan / 56074135100
dc.authorwosidGülsüm Gençoğlan / CQE-8195-2022en_US
dc.contributor.authorYılmaz, Abdurrahim
dc.contributor.authorGöktay, Fatih
dc.contributor.authorVarol, Rahmetullah
dc.contributor.authorGençoğlan, Gülsüm
dc.contributor.authorÜvet, Hüseyin
dc.date.accessioned2022-07-19T05:26:30Z
dc.date.available2022-07-19T05:26:30Z
dc.date.issued2022en_US
dc.departmentİstinye Üniversitesi, Tıp Fakültesi, Dahili Tıp Bilimleri Bölümüen_US
dc.description.abstractBackground: The diagnosis of superficial fungal infections is still mostly based on direct microscopic examination with Potassium Hydroxide solution. However, this method can be time consuming and its diagnostic accuracy rates vary widely depending on the clinician's experience. Objectives: This study presents a deep neural network structure that enables the rapid solutions for these problems and can perform automatic fungi detection in grayscale images without dyes. Methods: 160 microscopic full field photographs containing the fungal element, obtained from patients with onychomycosis, and 297 microscopic full field photographs containing dissolved keratin obtained from normal nails were collected. Smaller patches containing fungi (n=1835) and keratin (n=5238) were extracted from these full field images. In order to detect fungus and keratin, VGG16 and InceptionV3 models were developed by the use of these patches. The diagnostic performance of models was compared with 16 dermatologists by using 200 test patches. Results: For the VGG16 model, the InceptionV3 model and 16 dermatologists; mean accuracy rates were 88.10%±0.8%, 88.78%±0.35%, and 74.53%±8.57%, respectively; mean sensitivity rates were 75.04%±2.73%, 74.93%±4.52%, and 74.81%±19.51%, respectively; and mean specificity rates were 92.67%±1.17%, 93.78%±1.74%, and 74.25%±18.03%, respectively. The models were statistically superior to dermatologists according to rates of accuracy and specificity but not to sensitivity (p < 0.0001, p < 0.005, and p > 0.05, respectively). Area under curve values of the VGG16 and InceptionV3 models were 0.9339 and 0.9292, respectively. Conclusion: Our research demonstrates that it is possible to build an automated system capable of detecting fungi present in microscopic images employing the proposed deep learning models. It has great potential for fungal detection applications based on AI.en_US
dc.identifier.citationYilmaz A, Göktay F, Varol R, Gencoglan G, Uvet H. Deep Convolutional Neural Networks for Onychomycosis Detection using Microscopic Images with KOH Examination. Mycoses. 2022 Jul 16. doi: 10.1111/myc.13498. Epub ahead of print. PMID: 35842749.en_US
dc.identifier.doi10.1111/myc.13498en_US
dc.identifier.issn0933-7407en_US
dc.identifier.pmid35842749en_US
dc.identifier.scopus2-s2.0-85135195099en_US
dc.identifier.scopusqualityQ1en_US
dc.identifier.urihttp://doi.org/10.1111/myc.13498
dc.identifier.urihttps://hdl.handle.net/20.500.12713/3015
dc.identifier.wosWOS:000833600000001en_US
dc.identifier.wosqualityQ1en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.indekslendigikaynakPubMeden_US
dc.institutionauthorGençoğlan, Gülsüm
dc.language.isoenen_US
dc.publisherWileyen_US
dc.relation.ispartofMycosesen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectDeep Learningen_US
dc.subjectFungal Infectionsen_US
dc.subjectMicroscopic Imagesen_US
dc.subjectOnychomycosisen_US
dc.titleDeep convolutional neural networks for onychomycosis detection using microscopic images with KOH examinationen_US
dc.typeArticleen_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
Mycoses - 2022 - Yilmaz - Deep Convolutional Neural Networks for Onychomycosis Detection using Microscopic Images with KOH.pdf
Boyut:
1.97 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Tam Metin / Full Text
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
license.txt
Boyut:
1.44 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

PubMed İndeksli Yayınlar Koleksiyonu
Dahili Tıp Bilimleri Bölümü Makale Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu