{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T21:06:17Z","timestamp":1793653577562,"version":"4.5.1"},"reference-count":45,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T00:00:00Z","timestamp":1634515200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:p>\n                    <jats:bold>Background:<\/jats:bold>\n                    Today's machine-learning based dermatologic research has largely focused on pigmented\/non-pigmented lesions concerning skin cancers. However, studies on machine-learning-aided diagnosis of depigmented non-melanocytic lesions, which are more difficult to diagnose by unaided eye, are very few.\n                  <\/jats:p>\n                  <jats:p>\n                    <jats:bold>Objective:<\/jats:bold>\n                    We aim to assess the performance of deep learning methods for diagnosing vitiligo by deploying Convolutional Neural Networks (CNNs) and comparing their diagnosis accuracy with that of human raters with different levels of experience.\n                  <\/jats:p>\n                  <jats:p>\n                    <jats:bold>Methods:<\/jats:bold>\n                    A Chinese in-house dataset (2,876 images) and a world-wide public dataset (1,341 images) containing vitiligo and other depigmented\/hypopigmented lesions were constructed. Three CNN models were trained on close-up images in both datasets. The results by the CNNs were compared with those by 14 human raters from four groups: expert raters (&amp;gt;10 years of experience), intermediate raters (5\u201310 years), dermatology residents, and general practitioners. F1 score, the area under the receiver operating characteristic curve (AUC), specificity, and sensitivity metrics were used to compare the performance of the CNNs with that of the raters.\n                  <\/jats:p>\n                  <jats:p>\n                    <jats:bold>Results:<\/jats:bold>\n                    For the in-house dataset, CNNs achieved a comparable F1 score (mean [standard deviation]) with expert raters (0.8864 [0.005] vs. 0.8933 [0.044]) and outperformed intermediate raters (0.7603 [0.029]), dermatology residents (0.6161 [0.068]) and general practitioners (0.4964 [0.139]). For the public dataset, CNNs achieved a higher F1 score (0.9684 [0.005]) compared to the diagnosis of expert raters (0.9221 [0.031]).\n                  <\/jats:p>\n                  <jats:p>\n                    <jats:bold>Conclusion:<\/jats:bold>\n                    Properly designed and trained CNNs are able to diagnose vitiligo without the aid of Wood's lamp images and outperform human raters in an experimental setting.\n                  <\/jats:p>","DOI":"10.3389\/fmed.2021.754202","type":"journal-article","created":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T17:38:47Z","timestamp":1634578727000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":34,"title":["Design and Assessment of Convolutional Neural Network Based Methods for Vitiligo Diagnosis"],"prefix":"10.3389","volume":"8","author":[{"given":"Li","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suraj","family":"Mishra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Duo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yalin","family":"Lv","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingsong","family":"Lv","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nan","family":"Guan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaobo Sharon","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Danny Ziyi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiuping","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2021,10,18]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1056\/NEJMcp0804388","article-title":"Vitiligo","volume":"360","author":"Ta\u00efeb","year":"2009","journal-title":"N Engl J Med."},{"key":"B2","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1016\/j.det.2016.11.004","article-title":"Presentations, signs of activity, and differential diagnosis of vitiligo","volume":"35","author":"Goh","year":"2017","journal-title":"Dermatol Clin."},{"key":"B3","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1016\/j.jaad.2010.11.061","article-title":"Vitiligo: a comprehensive overview: part I. Introduction, epidemiology, quality of life, diagnosis, differential diagnosis, associations, histopathology, etiology, and work-up","volume":"65","author":"Alikhan","year":"2011","journal-title":"J Am Acad Dermatol."},{"key":"B4","doi-asserted-by":"publisher","first-page":"1051","DOI":"10.1111\/j.1365-2133.2008.08881.x","article-title":"Guideline for the diagnosis and management of vitiligo","volume":"159","author":"Gawkrodger","year":"2008","journal-title":"Br J Dermatol."},{"key":"B5","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1016\/j.jdermsci.2020.11.009","article-title":"A new deep learning approach integrated with clinical data for the dermoscopic differentiation of early melanomas from atypical nevi","volume":"101","author":"Tognetti","year":"2021","journal-title":"J Dermatol Sci."},{"key":"B6","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1038\/nature21056","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"Esteva","year":"2017","journal-title":"Nature."},{"key":"B7","doi-asserted-by":"publisher","first-page":"1529","DOI":"10.1016\/j.jid.2018.01.028","article-title":"Classification of the clinical images for benign and malignant cutaneous tumors using a deep learning algorithm","volume":"138","author":"Han","year":"2018","journal-title":"J Investig Dermatol."},{"key":"B8","doi-asserted-by":"publisher","first-page":"867","DOI":"10.1111\/bjd.15695","article-title":"A pretrained neural network shows similar diagnostic accuracy to medical students in categorizing dermatoscopic images after comparable training conditions","volume":"177","author":"Tschandl","year":"2017","journal-title":"Br J Dermatol."},{"key":"B9","doi-asserted-by":"publisher","first-page":"e1919396","DOI":"10.1001\/jamanetworkopen.2019.19396","article-title":"Assessment of a machine learning model applied to harmonized electronic health record data for the prediction of incident atrial fibrillation","volume":"3","author":"Tiwari","year":"2020","journal-title":"JAMA Netw Open"},{"key":"B10","doi-asserted-by":"publisher","first-page":"507","DOI":"10.1016\/j.jid.2019.12.029","article-title":"Research techniques made simple: deep learning for the classification of dermatological images","volume":"140","author":"Cullell-Dalmau","year":"2020","journal-title":"J Investig Dermatol."},{"key":"B11","doi-asserted-by":"publisher","first-page":"191","DOI":"10.3389\/fmed.2019.00191","article-title":"The possibility of deep learning-based, computer-aided skin tumor classifiers","volume":"6","author":"Fujisawa","year":"2019","journal-title":"Front Med."},{"key":"B12","doi-asserted-by":"publisher","first-page":"1105","DOI":"10.1001\/jamadermatol.2019.1633","article-title":"Marking the path toward artificial intelligence\u2013based image classification in dermatology","volume":"155","author":"Novoa","year":"2019","journal-title":"JAMA Dermatol."},{"key":"B13","doi-asserted-by":"publisher","first-page":"1504","DOI":"10.1016\/j.jid.2020.02.026","article-title":"Artificial intelligence in dermatology: a primer","volume":"140","author":"Young","year":"2020","journal-title":"J Investig Dermatol."},{"key":"B14","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1001\/jamadermatol.2018.4378","article-title":"Expert-level diagnosis of nonpigmented skin cancer by combined convolutional neural networks","volume":"155","author":"Tschandl","year":"2019","journal-title":"JAMA Dermatol."},{"key":"B15","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1111\/bjd.16924","article-title":"Deep-learning-based, computer-aided classifier developed with a small dataset of clinical images surpasses board-certified dermatologists in skin tumour diagnosis","volume":"180","author":"Fujisawa","year":"2019","journal-title":"Br J Dermatol."},{"key":"B16","doi-asserted-by":"publisher","first-page":"1388","DOI":"10.1111\/bjd.18459","article-title":"Dermatologist-level classification of malignant lip diseases using a deep convolutional neural network","volume":"182","author":"Cho","year":"2020","journal-title":"Br J Dermatol."},{"key":"B17","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.ejca.2020.04.043","article-title":"Past and present of computer-assisted dermoscopic diagnosis: performance of a conventional image analyser versus a convolutional neural network in a prospective data set of 1,981 skin lesions","volume":"135","author":"Sies","year":"2020","journal-title":"Eur J Cancer."},{"key":"B18","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1111\/jdv.15873","article-title":"Poor agreement between the automated risk assessment of a smartphone application for skin cancer detection and the rating by dermatologists","volume":"34","author":"Chung","year":"2020","journal-title":"J Eur Acad Dermatol Venereol."},{"key":"B19","doi-asserted-by":"publisher","first-page":"2199","DOI":"10.1001\/jama.2017.14585","article-title":"Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer","volume":"318","author":"Bejnordi","year":"2017","journal-title":"Jama."},{"key":"B20","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1001\/jamadermatol.2019.3807","article-title":"Keratinocytic skin cancer detection on the face using region-based convolutional neural network","volume":"156","author":"Han","year":"2020","journal-title":"JAMA Dermatol."},{"key":"B21","doi-asserted-by":"publisher","first-page":"900","DOI":"10.1038\/s41591-020-0842-3","article-title":"A deep learning system for differential diagnosis of skin diseases","volume":"26","author":"Liu","year":"2020","journal-title":"Nat Med."},{"key":"B22","doi-asserted-by":"crossref","first-page":"214","DOI":"10.1007\/978-3-030-35288-2","article-title":"Classification of vitiligo based on convolutional neural network","volume-title":"International Conference on Artificial Intelligence and Security 2019 Jul 26","author":"Liu","year":"2019"},{"key":"B23","first-page":"259","article-title":"Automatic classifier for skin disease using k-NN and SVM","volume-title":"Proceedings of the 2019 8th international conference on software and information engineering 2019 Apr 9","author":"Nosseir","year":""},{"key":"B24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s12652-020-02357-5","article-title":"An effective vitiligo intelligent classification system","author":"Luo","year":"2020","journal-title":"J Ambient Intell Humaniz Comput."},{"key":"B25","doi-asserted-by":"publisher","first-page":"1876","DOI":"10.1109\/TMI.2017.2695227","article-title":"Automatic skin lesion segmentation using deep fully convolutional networks with jaccard distance","volume":"36","author":"Yuan","year":"2017","journal-title":"IEEE Trans Med Imaging."},{"key":"B26","doi-asserted-by":"publisher","first-page":"1836","DOI":"10.1093\/annonc\/mdy166","article-title":"Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists","volume":"29","author":"Haenssle","year":"2018","journal-title":"Ann Oncol."},{"key":"B27","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.ejca.2019.04.001","article-title":"Deep learning outperformed 136 of 157 dermatologists in a head-to-head dermoscopic melanoma image classification task","volume":"113","author":"Brinker","year":"2019","journal-title":"Eur J Cancer."},{"key":"B28","doi-asserted-by":"publisher","first-page":"1261","DOI":"10.1111\/exd.13777","article-title":"Multimodal skin lesion classification using deep learning","volume":"27","author":"Yap","year":"2018","journal-title":"Exp Dermatol."},{"key":"B29","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1111\/bjd.18880","article-title":"What is AI? applications of artificial intelligence to dermatology","volume":"183","author":"Du-Harpur","year":"2020","journal-title":"Br J Dermatol."},{"key":"B30","unstructured":""},{"key":"B31","unstructured":""},{"key":"B32","unstructured":""},{"key":"B33","unstructured":""},{"key":"B34","unstructured":""},{"key":"B35","unstructured":""},{"key":"B36","unstructured":""},{"key":"B37","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"arXiv [Preprint] arXiv:1409.1556","author":"Simonyan","year":"2014"},{"key":"B38","first-page":"770","article-title":"Deep residual learning for image recognition","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"He","year":"2016"},{"key":"B39","first-page":"4700","article-title":"Densely connected convolutional networks","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Huang","year":"2017"},{"key":"B40","doi-asserted-by":"publisher","first-page":"1285","DOI":"10.1109\/TMI.2016.2528162","article-title":"Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning","volume":"35","author":"Shin","year":"2016","journal-title":"IEEE Trans Med Imaging."},{"key":"B41","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1109\/CVPR.2009.5206848","article-title":"Imagenet: a large-scale hierarchical image database","volume-title":"2009 IEEE conference on Computer Vision and Pattern Recognition","author":"Deng","year":"2009"},{"key":"B42","doi-asserted-by":"crossref","first-page":"1254","DOI":"10.1109\/ISBI45749.2020.9098403","article-title":"A data-aware deep supervised method for retinal vessel segmentation","volume-title":"2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI)","author":"Mishra","year":"2020"},{"key":"B43","article-title":"A closer look at domain shift for deep learning in histopathology","volume-title":"arXiv [Preprint] arXiv:1909.11575.","author":"Stacke","year":"2019"},{"key":"B44","doi-asserted-by":"publisher","first-page":"256","DOI":"10.1111\/srt.12422","article-title":"A feature fusion system for basal cell carcinoma detection through data-driven feature learning and patient profile","volume":"24","author":"Kharazmi","year":"2018","journal-title":"Skin Res Technol."},{"key":"B45","doi-asserted-by":"publisher","first-page":"1498","DOI":"10.1111\/bjd.18859","article-title":"A patient-oriented, general-practitioner-level, deep-learning-based cutaneous pigmented lesion risk classifier on a smartphone","volume":"182","author":"Chin","year":"2020","journal-title":"Br J Dermatol."}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2021.754202\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T17:39:50Z","timestamp":1634578790000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2021.754202\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,18]]},"references-count":45,"alternative-id":["10.3389\/fmed.2021.754202"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2021.754202","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,18]]},"article-number":"754202"}}