Cargando…

A Novel Convolutional Neural Network for the Diagnosis and Classification of Rosacea: Usability Study

BACKGROUND: Rosacea is a chronic inflammatory disease with variable clinical presentations, including transient flushing, fixed erythema, papules, pustules, and phymatous changes on the central face. Owing to the diversity in the clinical manifestations of rosacea, the lack of objective biochemical...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhao, Zhixiang, Wu, Che-Ming, Zhang, Shuping, He, Fanping, Liu, Fangfen, Wang, Ben, Huang, Yingxue, Shi, Wei, Jian, Dan, Xie, Hongfu, Yeh, Chao-Yuan, Li, Ji
Formato: Online Artículo Texto
Lenguaje:English
Publicado: JMIR Publications 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8077711/
https://www.ncbi.nlm.nih.gov/pubmed/33720027
http://dx.doi.org/10.2196/23415
_version_ 1783684930258075648
author Zhao, Zhixiang
Wu, Che-Ming
Zhang, Shuping
He, Fanping
Liu, Fangfen
Wang, Ben
Huang, Yingxue
Shi, Wei
Jian, Dan
Xie, Hongfu
Yeh, Chao-Yuan
Li, Ji
author_facet Zhao, Zhixiang
Wu, Che-Ming
Zhang, Shuping
He, Fanping
Liu, Fangfen
Wang, Ben
Huang, Yingxue
Shi, Wei
Jian, Dan
Xie, Hongfu
Yeh, Chao-Yuan
Li, Ji
author_sort Zhao, Zhixiang
collection PubMed
description BACKGROUND: Rosacea is a chronic inflammatory disease with variable clinical presentations, including transient flushing, fixed erythema, papules, pustules, and phymatous changes on the central face. Owing to the diversity in the clinical manifestations of rosacea, the lack of objective biochemical examinations, and nonspecificity in histopathological findings, accurate identification of rosacea is a big challenge. Artificial intelligence has emerged as a potential tool in the identification and evaluation of some skin diseases such as melanoma, basal cell carcinoma, and psoriasis. OBJECTIVE: The objective of our study was to utilize a convolutional neural network (CNN) to differentiate the clinical photos of patients with rosacea (taken from 3 different angles) from those of patients with other skin diseases such as acne, seborrheic dermatitis, and eczema that could be easily confused with rosacea. METHODS: In this study, 24,736 photos comprising of 18,647 photos of patients with rosacea and 6089 photos of patients with other skin diseases such as acne, facial seborrheic dermatitis, and eczema were included and analyzed by our CNN model based on ResNet-50. RESULTS: The CNN in our study achieved an overall accuracy and precision of 0.914 and 0.898, with an area under the receiver operating characteristic curve of 0.972 for the detection of rosacea. The accuracy of classifying 3 subtypes of rosacea, that is, erythematotelangiectatic rosacea, papulopustular rosacea, and phymatous rosacea was 83.9%, 74.3%, and 80.0%, respectively. Moreover, the accuracy and precision of our CNN to distinguish rosacea from acne reached 0.931 and 0.893, respectively. For the differentiation between rosacea, seborrheic dermatitis, and eczema, the overall accuracy of our CNN was 0.757 and the precision was 0.667. Finally, by comparing the CNN diagnosis with the diagnoses by dermatologists of different expertise levels, we found that our CNN system is capable of identifying rosacea with a performance superior to that of resident doctors or attending physicians and comparable to that of experienced dermatologists. CONCLUSIONS: The findings of our study showed that by assessing clinical images, the CNN system in our study could identify rosacea with accuracy and precision comparable to that of an experienced dermatologist.
format Online
Article
Text
id pubmed-8077711
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher JMIR Publications
record_format MEDLINE/PubMed
spelling pubmed-80777112021-05-06 A Novel Convolutional Neural Network for the Diagnosis and Classification of Rosacea: Usability Study Zhao, Zhixiang Wu, Che-Ming Zhang, Shuping He, Fanping Liu, Fangfen Wang, Ben Huang, Yingxue Shi, Wei Jian, Dan Xie, Hongfu Yeh, Chao-Yuan Li, Ji JMIR Med Inform Original Paper BACKGROUND: Rosacea is a chronic inflammatory disease with variable clinical presentations, including transient flushing, fixed erythema, papules, pustules, and phymatous changes on the central face. Owing to the diversity in the clinical manifestations of rosacea, the lack of objective biochemical examinations, and nonspecificity in histopathological findings, accurate identification of rosacea is a big challenge. Artificial intelligence has emerged as a potential tool in the identification and evaluation of some skin diseases such as melanoma, basal cell carcinoma, and psoriasis. OBJECTIVE: The objective of our study was to utilize a convolutional neural network (CNN) to differentiate the clinical photos of patients with rosacea (taken from 3 different angles) from those of patients with other skin diseases such as acne, seborrheic dermatitis, and eczema that could be easily confused with rosacea. METHODS: In this study, 24,736 photos comprising of 18,647 photos of patients with rosacea and 6089 photos of patients with other skin diseases such as acne, facial seborrheic dermatitis, and eczema were included and analyzed by our CNN model based on ResNet-50. RESULTS: The CNN in our study achieved an overall accuracy and precision of 0.914 and 0.898, with an area under the receiver operating characteristic curve of 0.972 for the detection of rosacea. The accuracy of classifying 3 subtypes of rosacea, that is, erythematotelangiectatic rosacea, papulopustular rosacea, and phymatous rosacea was 83.9%, 74.3%, and 80.0%, respectively. Moreover, the accuracy and precision of our CNN to distinguish rosacea from acne reached 0.931 and 0.893, respectively. For the differentiation between rosacea, seborrheic dermatitis, and eczema, the overall accuracy of our CNN was 0.757 and the precision was 0.667. Finally, by comparing the CNN diagnosis with the diagnoses by dermatologists of different expertise levels, we found that our CNN system is capable of identifying rosacea with a performance superior to that of resident doctors or attending physicians and comparable to that of experienced dermatologists. CONCLUSIONS: The findings of our study showed that by assessing clinical images, the CNN system in our study could identify rosacea with accuracy and precision comparable to that of an experienced dermatologist. JMIR Publications 2021-03-15 /pmc/articles/PMC8077711/ /pubmed/33720027 http://dx.doi.org/10.2196/23415 Text en ©Zhixiang Zhao, Che-Ming Wu, Shuping Zhang, Fanping He, Fangfen Liu, Ben Wang, Yingxue Huang, Wei Shi, Dan Jian, Hongfu Xie, Chao-Yuan Yeh, Ji Li. Originally published in JMIR Medical Informatics (http://medinform.jmir.org), 15.03.2021. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in JMIR Medical Informatics, is properly cited. The complete bibliographic information, a link to the original publication on http://medinform.jmir.org/, as well as this copyright and license information must be included.
spellingShingle Original Paper
Zhao, Zhixiang
Wu, Che-Ming
Zhang, Shuping
He, Fanping
Liu, Fangfen
Wang, Ben
Huang, Yingxue
Shi, Wei
Jian, Dan
Xie, Hongfu
Yeh, Chao-Yuan
Li, Ji
A Novel Convolutional Neural Network for the Diagnosis and Classification of Rosacea: Usability Study
title A Novel Convolutional Neural Network for the Diagnosis and Classification of Rosacea: Usability Study
title_full A Novel Convolutional Neural Network for the Diagnosis and Classification of Rosacea: Usability Study
title_fullStr A Novel Convolutional Neural Network for the Diagnosis and Classification of Rosacea: Usability Study
title_full_unstemmed A Novel Convolutional Neural Network for the Diagnosis and Classification of Rosacea: Usability Study
title_short A Novel Convolutional Neural Network for the Diagnosis and Classification of Rosacea: Usability Study
title_sort novel convolutional neural network for the diagnosis and classification of rosacea: usability study
topic Original Paper
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8077711/
https://www.ncbi.nlm.nih.gov/pubmed/33720027
http://dx.doi.org/10.2196/23415
work_keys_str_mv AT zhaozhixiang anovelconvolutionalneuralnetworkforthediagnosisandclassificationofrosaceausabilitystudy
AT wucheming anovelconvolutionalneuralnetworkforthediagnosisandclassificationofrosaceausabilitystudy
AT zhangshuping anovelconvolutionalneuralnetworkforthediagnosisandclassificationofrosaceausabilitystudy
AT hefanping anovelconvolutionalneuralnetworkforthediagnosisandclassificationofrosaceausabilitystudy
AT liufangfen anovelconvolutionalneuralnetworkforthediagnosisandclassificationofrosaceausabilitystudy
AT wangben anovelconvolutionalneuralnetworkforthediagnosisandclassificationofrosaceausabilitystudy
AT huangyingxue anovelconvolutionalneuralnetworkforthediagnosisandclassificationofrosaceausabilitystudy
AT shiwei anovelconvolutionalneuralnetworkforthediagnosisandclassificationofrosaceausabilitystudy
AT jiandan anovelconvolutionalneuralnetworkforthediagnosisandclassificationofrosaceausabilitystudy
AT xiehongfu anovelconvolutionalneuralnetworkforthediagnosisandclassificationofrosaceausabilitystudy
AT yehchaoyuan anovelconvolutionalneuralnetworkforthediagnosisandclassificationofrosaceausabilitystudy
AT liji anovelconvolutionalneuralnetworkforthediagnosisandclassificationofrosaceausabilitystudy
AT zhaozhixiang novelconvolutionalneuralnetworkforthediagnosisandclassificationofrosaceausabilitystudy
AT wucheming novelconvolutionalneuralnetworkforthediagnosisandclassificationofrosaceausabilitystudy
AT zhangshuping novelconvolutionalneuralnetworkforthediagnosisandclassificationofrosaceausabilitystudy
AT hefanping novelconvolutionalneuralnetworkforthediagnosisandclassificationofrosaceausabilitystudy
AT liufangfen novelconvolutionalneuralnetworkforthediagnosisandclassificationofrosaceausabilitystudy
AT wangben novelconvolutionalneuralnetworkforthediagnosisandclassificationofrosaceausabilitystudy
AT huangyingxue novelconvolutionalneuralnetworkforthediagnosisandclassificationofrosaceausabilitystudy
AT shiwei novelconvolutionalneuralnetworkforthediagnosisandclassificationofrosaceausabilitystudy
AT jiandan novelconvolutionalneuralnetworkforthediagnosisandclassificationofrosaceausabilitystudy
AT xiehongfu novelconvolutionalneuralnetworkforthediagnosisandclassificationofrosaceausabilitystudy
AT yehchaoyuan novelconvolutionalneuralnetworkforthediagnosisandclassificationofrosaceausabilitystudy
AT liji novelconvolutionalneuralnetworkforthediagnosisandclassificationofrosaceausabilitystudy