Deep convolutional neural networks for onychomycosis detection using microscopic images with KOH examination
Yükleniyor...
Tarih
2022
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Wiley
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
Background: 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.
Açıklama
Anahtar Kelimeler
Deep Learning, Fungal Infections, Microscopic Images, Onychomycosis
Kaynak
Mycoses
WoS Q Değeri
Q1
Scopus Q Değeri
Q1
Cilt
Sayı
Künye
Yilmaz 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.
