Back to Search Start Over

Deep neural networks show an equivalent and often superior performance to dermatologists in onychomycosis diagnosis: Automatic construction of onychomycosis datasets by region-based convolutional deep neural network.

Authors :
Seung Seog Han
Gyeong Hun Park
Woohyung Lim
Myoung Shin Kim
Jung Im Na
Ilwoo Park
Sung Eun Chang
Source :
PLoS ONE, Vol 13, Iss 1, p e0191493 (2018)
Publication Year :
2018
Publisher :
Public Library of Science (PLoS), 2018.

Abstract

Although there have been reports of the successful diagnosis of skin disorders using deep learning, unrealistically large clinical image datasets are required for artificial intelligence (AI) training. We created datasets of standardized nail images using a region-based convolutional neural network (R-CNN) trained to distinguish the nail from the background. We used R-CNN to generate training datasets of 49,567 images, which we then used to fine-tune the ResNet-152 and VGG-19 models. The validation datasets comprised 100 and 194 images from Inje University (B1 and B2 datasets, respectively), 125 images from Hallym University (C dataset), and 939 images from Seoul National University (D dataset). The AI (ensemble model; ResNet-152 + VGG-19 + feedforward neural networks) results showed test sensitivity/specificity/ area under the curve values of (96.0 / 94.7 / 0.98), (82.7 / 96.7 / 0.95), (92.3 / 79.3 / 0.93), (87.7 / 69.3 / 0.82) for the B1, B2, C, and D datasets. With a combination of the B1 and C datasets, the AI Youden index was significantly (p = 0.01) higher than that of 42 dermatologists doing the same assessment manually. For B1+C and B2+ D dataset combinations, almost none of the dermatologists performed as well as the AI. By training with a dataset comprising 49,567 images, we achieved a diagnostic accuracy for onychomycosis using deep learning that was superior to that of most of the dermatologists who participated in this study.

Subjects

Subjects :
Medicine
Science

Details

Language :
English
ISSN :
19326203
Volume :
13
Issue :
1
Database :
Directory of Open Access Journals
Journal :
PLoS ONE
Publication Type :
Academic Journal
Accession number :
edsdoj.6245cc5812b442c4940de6c12b3b821a
Document Type :
article
Full Text :
https://doi.org/10.1371/journal.pone.0191493