{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T01:58:51Z","timestamp":1788746331509,"version":"build-2803163510"},"reference-count":18,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2019,9,29]],"date-time":"2019-09-29T00:00:00Z","timestamp":1569715200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Skin Research and Technology"],"published-print":{"date-parts":[[2020,3]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>The visual assessment and severity grading of acne vulgaris by physicians can be subjective, resulting in inter\u2010 and intra\u2010observer variability.<\/jats:p><\/jats:sec><jats:sec><jats:title>Objective<\/jats:title><jats:p>To develop and validate an algorithm for the automated calculation of the Investigator's Global Assessment (IGA) scale, to standardize acne severity and outcome measurements.<\/jats:p><\/jats:sec><jats:sec><jats:title>Materials and Methods<\/jats:title><jats:p>A total of 472 photographs (retrieved 01\/01\/2004\u201004\/08\/2017) in the frontal view from 416 acne patients were used for training and testing. Photographs were labeled according to the IGA scale in three groups of IGA clear\/almost clear (0\u20101), IGA mild (2), and IGA moderate to severe (3\u20104). The classification model used a convolutional neural network, and models were separately trained on three image sizes. The photographs were then subjected to analysis by the algorithm, and the generated automated IGA scores were compared to clinical scoring. The prediction accuracy of each IGA grade label and the agreement (Pearson correlation) of the two scores were computed.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The best classification accuracy was 67%. Pearson correlation between machine\u2010predicted score and human labels (clinical scoring and researcher scoring) for each model and various image input sizes was 0.77. Correlation of predictions with clinical scores was highest when using Inception v4 on the largest image size of 1200\u00a0\u00d7\u00a01600. Two sets of human labels showed a high correlation of 0.77, verifying the repeatability of the ground truth labels. Confusion matrices show that the models performed sub\u2010optimally on the IGA 2 label.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>Deep learning techniques harnessing high\u2010resolution images and large datasets will continue to improve, demonstrating growing potential for automated clinical image analysis and grading.<\/jats:p><\/jats:sec>","DOI":"10.1111\/srt.12794","type":"journal-article","created":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T02:39:17Z","timestamp":1569897557000},"page":"187-192","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":45,"title":["Automated grading of acne vulgaris by deep learning with convolutional neural networks"],"prefix":"10.1111","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4620-6843","authenticated-orcid":false,"given":"Ziying Vanessa","family":"Lim","sequence":"first","affiliation":[{"name":"National Skin Centre Singapore Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Farhan","family":"Akram","sequence":"additional","affiliation":[{"name":"Bioinformatics Institute Agency for Science, Technology and Research (A*STAR) Singapore Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cuong Phuc","family":"Ngo","sequence":"additional","affiliation":[{"name":"Bioinformatics Institute Agency for Science, Technology and Research (A*STAR) Singapore Singapore"},{"name":"Hwa Chong Institution Singapore Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amadeus Aristo","family":"Winarto","sequence":"additional","affiliation":[{"name":"Bioinformatics Institute Agency for Science, Technology and Research (A*STAR) Singapore Singapore"},{"name":"Hwa Chong Institution Singapore Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei Qing","family":"Lee","sequence":"additional","affiliation":[{"name":"School of Computing National University of Singapore Singapore Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaicheng","family":"Liang","sequence":"additional","affiliation":[{"name":"Bioinformatics Institute Agency for Science, Technology and Research (A*STAR) Singapore Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7607-3124","authenticated-orcid":false,"given":"Hazel Hweeboon","family":"Oon","sequence":"additional","affiliation":[{"name":"National Skin Centre Singapore Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Steven Tien Guan","family":"Thng","sequence":"additional","affiliation":[{"name":"National Skin Centre Singapore Singapore"},{"name":"Skin Research Institute Singapore A*STAR Singapore Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hwee Kuan","family":"Lee","sequence":"additional","affiliation":[{"name":"Bioinformatics Institute Agency for Science, Technology and Research (A*STAR) Singapore Singapore"},{"name":"School of Computing National University of Singapore Singapore Singapore"},{"name":"Image and Pervasive Access Lab CNRS Singapore Singapore"},{"name":"Singapore Eye Research Institute Singapore Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2019,9,29]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1111\/bjd.13462"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1346-8138.2007.00403.x-i1"},{"key":"e_1_2_8_4_1","unstructured":"Research C. for D. E. and. Acne vulgaris: establishing effectiveness of drugs intended for treatment. U.S. Food and Drug Administration. Available at:http:\/\/www.fda.gov\/regulatory-information\/search-fda-guidance-documents\/acne-vulgaris-establishing-effectiveness-drugs-intended-treatment. Accessed June 20 2019."},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.clindermatol.2016.10.006"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1468-3083.2009.03278.x"},{"key":"e_1_2_8_7_1","doi-asserted-by":"crossref","unstructured":"AlamdariN TavakolianK AlhashimM et al.Detection and classification of acne lesions in acne patients: a mobile application. 2016 IEEE International Conference on Electro Information Technology Grand Forks ND2016 pp.0739\u20100743.","DOI":"10.1109\/EIT.2016.7535331"},{"key":"e_1_2_8_8_1","doi-asserted-by":"crossref","unstructured":"MaroniGErmidoroMPrevidiF.Automated detection extraction and counting of acne lesions for automatic evaluation and tracking of acne severity. 2017 IEEE Symposium Series on Computational Intelligence Honolulu HI2017 pp.1\u20106.","DOI":"10.1109\/SSCI.2017.8280925"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1111\/bjd.13699"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1111\/bjd.16563"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature22985"},{"key":"e_1_2_8_12_1","doi-asserted-by":"crossref","unstructured":"LiX WuJ JiangH et al.Skin lesion classification via combining deep learning features and clinical criteria representations. Available at:https:\/\/www.biorxiv.org\/content\/10.1101\/382010v1Accessed May 19 2019.","DOI":"10.1101\/382010"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-24204-6"},{"issue":"9","key":"e_1_2_8_14_1","first-page":"1006","article-title":"Artificial intelligence for the objective evaluation of acne investigator global assessment","volume":"17","author":"Melina A","year":"2018","journal-title":"J Drugs Dermatol"},{"issue":"4","key":"e_1_2_8_15_1","first-page":"381","article-title":"Classification model of facial acne using deep learning","volume":"23","author":"Jung C","year":"2019","journal-title":"J Korea Inst Inf Commun Eng"},{"key":"e_1_2_8_16_1","doi-asserted-by":"crossref","unstructured":"HuangG LiuZ van derMaatenL et al.Densely Connected Convolutional Networks. Available at:http:\/\/arxiv.org\/abs\/1608.06993Accessed May 2 2019.","DOI":"10.17504\/protocols.io.8j6hure"},{"key":"e_1_2_8_17_1","unstructured":"SzegedyC IoffeS VanhouckeV et al.Inception\u2010ResNet and the impact of residual connections on learning. Available at:http:\/\/arxiv.org\/abs\/1602.07261Accessed May 30 2019."},{"key":"e_1_2_8_18_1","unstructured":"HeK ZhangX RenS et al.Deep residual learning for image recognition. Available at:http:\/\/arxiv.org\/abs\/1512.03385Accessed October 4 2018."},{"key":"e_1_2_8_19_1","unstructured":"AndringaPC ZhangH ZhaoT et al.Assessing the severity of acne via cell phone selfie images using a deep learning model. Available at:https:\/\/www.microsoft.com\/developerblog\/2019\/02\/05\/assessing-the-severity-of-acne-via-cell-phone-selfie-images-using-a-deep-learning-model\/Accessed June 30 2019."}],"container-title":["Skin Research and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1111%2Fsrt.12794","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/srt.12794","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/srt.12794","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/srt.12794","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,3]],"date-time":"2023-09-03T12:09:05Z","timestamp":1693742945000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/srt.12794"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9,29]]},"references-count":18,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2020,3]]}},"alternative-id":["10.1111\/srt.12794"],"URL":"https:\/\/doi.org\/10.1111\/srt.12794","archive":["Portico"],"relation":{},"ISSN":["0909-752X","1600-0846"],"issn-type":[{"value":"0909-752X","type":"print"},{"value":"1600-0846","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,9,29]]},"assertion":[{"value":"2019-08-03","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-09-05","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-09-29","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}