Cargando…
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
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...
Autores principales: | , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Public Library of Science
2018
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5774804/ https://www.ncbi.nlm.nih.gov/pubmed/29352285 http://dx.doi.org/10.1371/journal.pone.0191493 |
_version_ | 1783293815284563968 |
---|---|
author | Han, Seung Seog Park, Gyeong Hun Lim, Woohyung Kim, Myoung Shin Na, Jung Im Park, Ilwoo Chang, Sung Eun |
author_facet | Han, Seung Seog Park, Gyeong Hun Lim, Woohyung Kim, Myoung Shin Na, Jung Im Park, Ilwoo Chang, Sung Eun |
author_sort | Han, Seung Seog |
collection | PubMed |
description | 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. |
format | Online Article Text |
id | pubmed-5774804 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2018 |
publisher | Public Library of Science |
record_format | MEDLINE/PubMed |
spelling | pubmed-57748042018-02-05 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 Han, Seung Seog Park, Gyeong Hun Lim, Woohyung Kim, Myoung Shin Na, Jung Im Park, Ilwoo Chang, Sung Eun PLoS One Research Article 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. Public Library of Science 2018-01-19 /pmc/articles/PMC5774804/ /pubmed/29352285 http://dx.doi.org/10.1371/journal.pone.0191493 Text en © 2018 Han et al http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. |
spellingShingle | Research Article Han, Seung Seog Park, Gyeong Hun Lim, Woohyung Kim, Myoung Shin Na, Jung Im Park, Ilwoo Chang, Sung Eun 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 |
title | 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 |
title_full | 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 |
title_fullStr | 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 |
title_full_unstemmed | 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 |
title_short | 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 |
title_sort | 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 |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5774804/ https://www.ncbi.nlm.nih.gov/pubmed/29352285 http://dx.doi.org/10.1371/journal.pone.0191493 |
work_keys_str_mv | AT hanseungseog deepneuralnetworksshowanequivalentandoftensuperiorperformancetodermatologistsinonychomycosisdiagnosisautomaticconstructionofonychomycosisdatasetsbyregionbasedconvolutionaldeepneuralnetwork AT parkgyeonghun deepneuralnetworksshowanequivalentandoftensuperiorperformancetodermatologistsinonychomycosisdiagnosisautomaticconstructionofonychomycosisdatasetsbyregionbasedconvolutionaldeepneuralnetwork AT limwoohyung deepneuralnetworksshowanequivalentandoftensuperiorperformancetodermatologistsinonychomycosisdiagnosisautomaticconstructionofonychomycosisdatasetsbyregionbasedconvolutionaldeepneuralnetwork AT kimmyoungshin deepneuralnetworksshowanequivalentandoftensuperiorperformancetodermatologistsinonychomycosisdiagnosisautomaticconstructionofonychomycosisdatasetsbyregionbasedconvolutionaldeepneuralnetwork AT najungim deepneuralnetworksshowanequivalentandoftensuperiorperformancetodermatologistsinonychomycosisdiagnosisautomaticconstructionofonychomycosisdatasetsbyregionbasedconvolutionaldeepneuralnetwork AT parkilwoo deepneuralnetworksshowanequivalentandoftensuperiorperformancetodermatologistsinonychomycosisdiagnosisautomaticconstructionofonychomycosisdatasetsbyregionbasedconvolutionaldeepneuralnetwork AT changsungeun deepneuralnetworksshowanequivalentandoftensuperiorperformancetodermatologistsinonychomycosisdiagnosisautomaticconstructionofonychomycosisdatasetsbyregionbasedconvolutionaldeepneuralnetwork |