{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T20:25:09Z","timestamp":1789244709511,"version":"build-2803163510"},"reference-count":18,"publisher":"Wiley","issue":"12","license":[{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100011318","name":"Fondation Botnar","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011318","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010314","name":"Helmut Fischer Stiftung","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010314","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100008375","name":"Universit\u00e4t Basel","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008375","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Acad Dermatol Venereol"],"published-print":{"date-parts":[[2022,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>The exact location of skin lesions is key in clinical dermatology. On one hand, it supports differential diagnosis (DD) since most skin conditions have specific predilection sites. On the other hand, location matters for dermatosurgical interventions. In practice, lesion evaluation is not well standardized and anatomical descriptions vary or lack altogether. Automated determination of anatomical location could benefit both situations.<\/jats:p><\/jats:sec><jats:sec><jats:title>Objective<\/jats:title><jats:p>Establish an automated method to determine anatomical regions in clinical patient pictures and evaluate the gain in DD performance of a deep learning model (DLM) when trained with lesion locations and images.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>Retrospective study based on three datasets: macro\u2010anatomy for the main body regions with 6000 patient pictures partially labelled by a student, micro\u2010anatomy for the ear region with 182 pictures labelled by a student and DD with 3347 pictures of 16 diseases determined by dermatologists in clinical settings. For each dataset, a DLM was trained and evaluated on an independent test set. The primary outcome measures were the precision and sensitivity with 95% CI. For DD, we compared the performance of a DLM trained with lesion pictures only with a DLM trained with both pictures and locations.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The average precision and sensitivity were 85% (CI 84\u201386), 84% (CI 83\u201385) for macro\u2010anatomy, 81% (CI 80\u201383), 80% (CI 77\u201383) for micro\u2010anatomy and 82% (CI 78\u201385), 81% (CI 77\u201384) for DD. We observed an improvement in DD performance of 6% (McNemar test <jats:italic>P<\/jats:italic>\u2010value 0.0009) for both average precision and sensitivity when training with both lesion pictures and locations.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>Including location can be beneficial for DD DLM performance. The proposed method can generate body region maps from patient pictures and even reach surgery relevant anatomical precision, e.g. the ear region. Our method enables automated search of large clinical databases and make targeted anatomical image retrieval possible.<\/jats:p><\/jats:sec>","DOI":"10.1111\/jdv.18476","type":"journal-article","created":{"date-parts":[[2022,8,4]],"date-time":"2022-08-04T07:53:54Z","timestamp":1659599634000},"page":"2525-2532","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Improved diagnosis by automated macro\u2010 and micro\u2010anatomical region mapping of skin photographs"],"prefix":"10.1111","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5980-5469","authenticated-orcid":false,"given":"L.","family":"Amruthalingam","sequence":"first","affiliation":[{"name":"Department of Biomedical Engineering University of Basel  Basel Switzerland"},{"name":"Lucerne School of Computer Science and Information Technology Lucerne University of Applied Sciences and Arts  Lucerne Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"P.","family":"Gottfrois","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering University of Basel  Basel Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"A.","family":"Gonzalez Jimenez","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering University of Basel  Basel Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"B.","family":"G\u00f6kduman","sequence":"additional","affiliation":[{"name":"Lucerne School of Computer Science and Information Technology Lucerne University of Applied Sciences and Arts  Lucerne Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"M.","family":"Kunz","sequence":"additional","affiliation":[{"name":"Department of Health Sciences and Technology Swiss Federal Institute of Technology  Zurich Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"T.","family":"Koller","sequence":"additional","affiliation":[{"name":"Department of Dermatology University Hospital of Basel  Basel Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"name":"DERMANATOMY Consortium","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"M.","family":"Pouly","sequence":"additional","affiliation":[{"name":"Department of Dermatology University Hospital of Basel  Basel Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7059-632X","authenticated-orcid":false,"given":"A.A.","family":"Navarini","sequence":"additional","affiliation":[{"name":"Department of Health Sciences and Technology Swiss Federal Institute of Technology  Zurich Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2022,9]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.clindermatol.2011.03.003"},{"key":"e_1_2_11_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jaad.2018.08.035"},{"key":"e_1_2_11_4_1","doi-asserted-by":"publisher","DOI":"10.1097\/JDN.0000000000000154"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jaad.2015.12.019"},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_2_11_7_1","first-page":"6105","volume-title":"International Conference on Machine Learning","author":"Tan M","year":"2019"},{"key":"e_1_2_11_8_1","unstructured":"YalnizIZ J\u00e9gouH ChenK PaluriM MahajanD.Billion\u2010scale semi\u2010supervised learning for image classification. arXiv preprint arXiv:1905.00546.2019."},{"key":"e_1_2_11_9_1","unstructured":"SmithLN.A disciplined approach to neural network hyper\u2010parameters: part 1\u2010learning rate batch size momentum and weight decay. arXiv preprint arXiv:1803.09820.2018."},{"key":"e_1_2_11_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_11_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_11_12_1","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300017197"},{"key":"e_1_2_11_13_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13300"},{"key":"e_1_2_11_14_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/abfbf4"},{"key":"e_1_2_11_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_3"},{"key":"e_1_2_11_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-57321-8_11"},{"key":"e_1_2_11_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2021.3062002"},{"key":"e_1_2_11_18_1","unstructured":"LiaoH LuoJ.A deep multi\u2010task learning approach to skin lesion classification. arXiv preprint arXiv:1812.03527.2018."},{"key":"e_1_2_11_19_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamadermatol.2021.4915"}],"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.18476","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/jdv.18476","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/jdv.18476","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T16:11:08Z","timestamp":1692634268000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/jdv.18476"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9]]},"references-count":18,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["10.1111\/jdv.18476"],"URL":"https:\/\/doi.org\/10.1111\/jdv.18476","archive":["Portico"],"relation":{},"ISSN":["0926-9959","1468-3083"],"issn-type":[{"value":"0926-9959","type":"print"},{"value":"1468-3083","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9]]},"assertion":[{"value":"2022-03-22","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-06-30","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-09-01","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}