{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T01:12:30Z","timestamp":1787015550971,"version":"build-2736575974"},"reference-count":32,"publisher":"Wiley","issue":"5","license":[{"start":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T00:00:00Z","timestamp":1674777600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Acad Dermatol Venereol"],"published-print":{"date-parts":[[2023,5]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Artificial intelligence (AI) and convolutional neural networks (CNNs) represent rising trends in modern medicine. However, comprehensive data on the performance of AI practices in clinical dermatologic images are non\u2010existent. Furthermore, the role of professional data selection for training remains unknown.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>The aims of this study were to develop AI applications for outlier detection of dermatological pathologies, to evaluate CNN architectures' performance on dermatological images and to investigate the role of professional pre\u2010processing of the training data, serving as one of the first anchor points regarding data selection criteria in dermatological AI\u2010based binary classification tasks of non\u2010melanoma pathologies.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Six state\u2010of\u2010the\u2010art CNN architectures were evaluated for their accuracy, sensitivity and specificity for five dermatological diseases and using five data subsets, including data selected by two dermatologists, one with 5 and the other with 11\u2009years of clinical experience.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Overall, 150 CNNs were evaluated on up to 4051 clinical images. The best accuracy was reached for onychomycosis (accuracy\u00a0=\u00a01.000), followed by bullous pemphigoid (accuracy\u00a0=\u00a00.951) and lupus erythematosus (accuracy\u00a0=\u00a00.912). The CNNs InceptionV3, Xception and ResNet50 achieved the best accuracy in 9, 8 and 6 out of 25 data sets, respectively (36.0%, 32.0% and 24.0%). On average, the data set provided by the senior physician and the data set provided in accordance with both dermatologists performed the best (accuracy\u00a0=\u00a00.910).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This AI approach for the detection of outliers in dermatological diagnoses represents one of the first studies to evaluate the performance of different CNNs for binary decisions in clinical non\u2010dermatoscopic images of a variety of dermatological diseases other than melanoma. The selection of images by an experienced dermatologist during pre\u2010processing had substantial benefits for the performance of the CNNs. These comparative results might guide future AI approaches to dermatology diagnostics, and the evaluated CNNs might be applicable for the future training of dermatology residents.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1111\/jdv.18853","type":"journal-article","created":{"date-parts":[[2023,1,6]],"date-time":"2023-01-06T05:59:32Z","timestamp":1672984772000},"page":"1071-1079","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":31,"title":["Outlier detection in dermatology: Performance of different convolutional neural networks for binary classification of inflammatory skin diseases"],"prefix":"10.1111","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3767-1337","authenticated-orcid":false,"given":"Maximilian C.","family":"Schielein","sequence":"first","affiliation":[{"name":"Department of Dermatology and Allergy, School of Medicine Technical University of Munich  Munich Germany"},{"name":"Unit of Dermatology and Venerology, Department of Medicine, Karolinska Institutet Karolinska University Hospital  Stockholm Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5364-9418","authenticated-orcid":false,"given":"Joshua","family":"Christl","sequence":"additional","affiliation":[{"name":"Department of Informatics and Munich School of BioEngineering Technical University of Munich  Munich Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7324-9139","authenticated-orcid":false,"given":"Sebastian","family":"Sitaru","sequence":"additional","affiliation":[{"name":"Department of Dermatology and Allergy, School of Medicine Technical University of Munich  Munich Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3028-4556","authenticated-orcid":false,"given":"Anna Caroline","family":"Pilz","sequence":"additional","affiliation":[{"name":"Department of Dermatology and Allergy, School of Medicine Technical University of Munich  Munich Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8570-1601","authenticated-orcid":false,"given":"Robert","family":"Kaczmarczyk","sequence":"additional","affiliation":[{"name":"Department of Dermatology and Allergy, School of Medicine Technical University of Munich  Munich Germany"},{"name":"Unit of Dermatology and Venerology, Department of Medicine, Karolinska Institutet Karolinska University Hospital  Stockholm Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5352-5105","authenticated-orcid":false,"given":"Tilo","family":"Biedermann","sequence":"additional","affiliation":[{"name":"Department of Dermatology and Allergy, School of Medicine Technical University of Munich  Munich Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5669-920X","authenticated-orcid":false,"given":"Tobias","family":"Lasser","sequence":"additional","affiliation":[{"name":"Department of Informatics and Munich School of BioEngineering Technical University of Munich  Munich Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9313-6588","authenticated-orcid":false,"given":"Alexander","family":"Zink","sequence":"additional","affiliation":[{"name":"Department of Dermatology and Allergy, School of Medicine Technical University of Munich  Munich Germany"},{"name":"Unit of Dermatology and Venerology, Department of Medicine, Karolinska Institutet Karolinska University Hospital  Stockholm Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2023,1,27]]},"reference":[{"key":"e_1_2_11_2_1","volume-title":"Artificial intelligence. A modern approach","author":"Russell SJ","year":"2022"},{"key":"e_1_2_11_3_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746\u2010020\u201000376\u20102"},{"key":"e_1_2_11_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00105\u2010020\u201004663\u20107"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.1111\/bjd.18880"},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591\u2010020\u20100842\u20103"},{"key":"e_1_2_11_7_1","volume-title":"Machine learning","author":"Mitchell TM","year":"1997"},{"key":"e_1_2_11_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejca.2019.07.019"},{"key":"e_1_2_11_9_1","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2020.00233"},{"key":"e_1_2_11_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00105\u2010020\u201004662\u20108"},{"key":"e_1_2_11_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00105\u2010020\u201004657\u20105"},{"key":"e_1_2_11_12_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365\u20102133.2011.10436.x"},{"key":"e_1_2_11_13_1","doi-asserted-by":"publisher","DOI":"10.1038\/jid.2013.446"},{"key":"e_1_2_11_14_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.m1590"},{"key":"e_1_2_11_15_1","doi-asserted-by":"publisher","DOI":"10.2340\/00015555\u20103510"},{"key":"e_1_2_11_16_1","doi-asserted-by":"publisher","DOI":"10.1111\/bjd.17818"},{"key":"e_1_2_11_17_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen\u20102020\u2010043926"},{"key":"e_1_2_11_18_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746\u2010020\u201000380\u20106"},{"key":"e_1_2_11_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejca.2021.05.026"},{"key":"e_1_2_11_20_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature21056"},{"key":"e_1_2_11_21_1","doi-asserted-by":"publisher","DOI":"10.2316\/P.2017.852-053"},{"key":"e_1_2_11_22_1","doi-asserted-by":"publisher","DOI":"10.3390\/s18020556"},{"key":"e_1_2_11_23_1","doi-asserted-by":"publisher","DOI":"10.2196\/11936"},{"key":"e_1_2_11_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263\u2010015\u20100816\u2010y"},{"key":"e_1_2_11_25_1","doi-asserted-by":"publisher","DOI":"10.1177\/1464993413490479"},{"key":"e_1_2_11_26_1","unstructured":"SimonyanK ZissermanA.Very deep convolutional networks for large\u2010scale image recognition[2014 Sep 04]."},{"key":"e_1_2_11_27_1","unstructured":"CholletF.Xception: deep learning with depthwise separable convolutions[2016 Oct 07]."},{"key":"e_1_2_11_28_1","unstructured":"SzegedyC VanhouckeV IoffeS ShlensJ WojnaZ.Rethinking the inception architecture for computer vision[2015 Dec 02]."},{"key":"e_1_2_11_29_1","unstructured":"HeK ZhangX RenS SunJ.Deep residual learning for image recognition[2015 Dec 10]."},{"key":"e_1_2_11_30_1","unstructured":"SandlerM HowardA ZhuM ZhmoginovA ChenL\u2010C.MobileNetV2: inverted residuals and linear bottlenecks.The IEEE Conference on Computer Vision and Pattern Recognition(CVPR)."},{"key":"e_1_2_11_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521\u2010020\u201005394\u20105"},{"key":"e_1_2_11_32_1","doi-asserted-by":"publisher","DOI":"10.2196\/18091"},{"key":"e_1_2_11_33_1","doi-asserted-by":"publisher","DOI":"10.21037\/atm.2020.04.39"}],"container-title":["Journal of the European Academy of Dermatology and Venereology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/jdv.18853","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/jdv.18853","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/jdv.18853","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T14:26:38Z","timestamp":1692627998000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/jdv.18853"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,27]]},"references-count":32,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2023,5]]}},"alternative-id":["10.1111\/jdv.18853"],"URL":"https:\/\/doi.org\/10.1111\/jdv.18853","archive":["Portico"],"relation":{},"ISSN":["0926-9959","1468-3083"],"issn-type":[{"value":"0926-9959","type":"print"},{"value":"1468-3083","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,27]]},"assertion":[{"value":"2022-01-03","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-11-10","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-01-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}