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
- Source :
- PLoS ONE, Vol 13, Iss 1, p e0191493 (2018), PLoS ONE
- 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 :
- Male
0301 basic medicine
Databases, Factual
Computer science
Social Sciences
lcsh:Medicine
Pathology and Laboratory Medicine
Convolutional neural network
Machine Learning
030207 dermatology & venereal diseases
Learning and Memory
0302 clinical medicine
Medicine and Health Sciences
Psychology
Diagnosis, Computer-Assisted
lcsh:Science
Multidisciplinary
Artificial neural network
Middle Aged
Oncology
Area Under Curve
Feedforward neural network
Deep neural networks
Female
Algorithms
Research Article
Adult
Computer and Information Sciences
Neural Networks
Dermatology
Hand Dermatoses
Hair and Nail Diseases
Human Learning
Young Adult
03 medical and health sciences
Signs and Symptoms
Diagnostic Medicine
Artificial Intelligence
Image Interpretation, Computer-Assisted
Onychomycosis
Cancer Detection and Diagnosis
Learning
Humans
Artificial Neural Networks
Aged
Computational Neuroscience
Foot Dermatoses
business.industry
Deep learning
lcsh:R
Cognitive Psychology
Biology and Life Sciences
Computational Biology
Pattern recognition
030104 developmental biology
Lesions
Cognitive Science
lcsh:Q
Neural Networks, Computer
Artificial intelligence
business
Neuroscience
Dermatologists
Subjects
Details
- Language :
- English
- ISSN :
- 19326203
- Volume :
- 13
- Issue :
- 1
- Database :
- OpenAIRE
- Journal :
- PLoS ONE
- Accession number :
- edsair.doi.dedup.....4deaf5c622ea394fbd260e74ebf0cc2e