{"title":"Intelligent Diagnosis of Hypopigmented Dermatoses and Intelligent Evaluation of Vitiligo Severity on the Basis of Deep Learning.","authors":"Hequn Huang, Changqing Wang, Geng Gao, Zhuangzhuang Fan, Lulu Ren, Rui Wang, Zhu Chen, Maoxin Huang, Mei Li, Fei Yang, Fengli Xiao","doi":"10.1007/s13555-024-01296-9","DOIUrl":null,"url":null,"abstract":"<p><strong>Introduction: </strong>There is a lack of objective, accurate, and convenient methods for classification diagnostic hypopigmented dermatoses (HD) and severity evaluation of vitiligo. To achieve an accurate and intelligent classification diagnostic model of HD and severity evaluation model of vitiligo using a deep learning-based method.</p><p><strong>Methods: </strong>A total of 11,483 images from 4744 patients with HD were included in this study. An optimal diagnostic model was constructed by merging the squeeze-and-excitation (SE) module with the candidate model, its diagnostic efficiency was compared with that of 98 dermatologists. An objective severity evaluation indicator was proposed through weighting method and combined with a segmentation model to form a severity evaluation model, which was then compared with the assessments conducted by three experienced dermatologists using the naked eye.</p><p><strong>Results: </strong>The improved diagnosis model SE_ResNet-18 outperformed the other 11 classic models with an accuracy of 0.9389, macro-specificity of 0.9878, and macro-f1 score of 0.9395, and outperformed the different categories of 98 dermatologists (P < 0.001). The weighted Kappa test indicated medium consistency between the Indicator<sub>v</sub> and the VASI<sub>change</sub> (K = 0.567, P < 0.05). The optimal segmented model, HR-Net, had 0.8421 mIOU. The model-based severity evaluation results were not significantly different among the three experienced dermatologists.</p><p><strong>Conclusions: </strong>This study proposes an objective, accurate, and convenient hybrid model for diagnosing HD and evaluating the severity of vitiligo, providing a method for dermatologists especially in grassroots hospitals, and provides a foundation for telemedicine.</p>","PeriodicalId":11186,"journal":{"name":"Dermatology and Therapy","volume":" ","pages":"3307-3320"},"PeriodicalIF":3.5000,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11604898/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Dermatology and Therapy","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s13555-024-01296-9","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/11/8 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"DERMATOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Introduction: There is a lack of objective, accurate, and convenient methods for classification diagnostic hypopigmented dermatoses (HD) and severity evaluation of vitiligo. To achieve an accurate and intelligent classification diagnostic model of HD and severity evaluation model of vitiligo using a deep learning-based method.
Methods: A total of 11,483 images from 4744 patients with HD were included in this study. An optimal diagnostic model was constructed by merging the squeeze-and-excitation (SE) module with the candidate model, its diagnostic efficiency was compared with that of 98 dermatologists. An objective severity evaluation indicator was proposed through weighting method and combined with a segmentation model to form a severity evaluation model, which was then compared with the assessments conducted by three experienced dermatologists using the naked eye.
Results: The improved diagnosis model SE_ResNet-18 outperformed the other 11 classic models with an accuracy of 0.9389, macro-specificity of 0.9878, and macro-f1 score of 0.9395, and outperformed the different categories of 98 dermatologists (P < 0.001). The weighted Kappa test indicated medium consistency between the Indicatorv and the VASIchange (K = 0.567, P < 0.05). The optimal segmented model, HR-Net, had 0.8421 mIOU. The model-based severity evaluation results were not significantly different among the three experienced dermatologists.
Conclusions: This study proposes an objective, accurate, and convenient hybrid model for diagnosing HD and evaluating the severity of vitiligo, providing a method for dermatologists especially in grassroots hospitals, and provides a foundation for telemedicine.
期刊介绍:
Dermatology and Therapy is an international, open access, peer-reviewed, rapid publication journal (peer review in 2 weeks, published 3–4 weeks from acceptance). The journal is dedicated to the publication of high-quality clinical (all phases), observational, real-world, and health outcomes research around the discovery, development, and use of dermatological therapies. Studies relating to diagnosis, pharmacoeconomics, public health and epidemiology, quality of life, and patient care, management, and education are also encouraged.
Areas of focus include, but are not limited to all clinical aspects of dermatology, such as skin pharmacology; skin development and aging; prevention, diagnosis, and management of skin disorders and melanomas; research into dermal structures and pathology; and all areas of aesthetic dermatology, including skin maintenance, dermatological surgery, and lasers.
The journal is of interest to a broad audience of pharmaceutical and healthcare professionals and publishes original research, reviews, case reports/case series, trial protocols, and short communications. Dermatology and Therapy will consider all scientifically sound research be it positive, confirmatory or negative data. Submissions are welcomed whether they relate to an International and/or a country-specific audience, something that is crucially important when researchers are trying to target more specific patient populations. This inclusive approach allows the journal to assist in the dissemination of quality research, which may be considered of insufficient interest by other journals. The journal appeals to a global audience and receives submissions from all over the world.