{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T10:57:22Z","timestamp":1788173842046,"version":"build-2803163510"},"update-to":[{"DOI":"10.1371\/journal.pntd.0011230","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2023,8,24]],"date-time":"2023-08-24T00:00:00Z","timestamp":1692835200000}}],"reference-count":26,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2023,8,14]],"date-time":"2023-08-14T00:00:00Z","timestamp":1691971200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000061","name":"Fogarty International Center","doi-asserted-by":"publisher","award":["R21TW011860"],"award-info":[{"award-number":["R21TW011860"]}],"id":[{"id":"10.13039\/100000061","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100009619","name":"Japan Agency for Medical Research and Development","doi-asserted-by":"publisher","award":["21jm0510004h0204"],"award-info":[{"award-number":["21jm0510004h0204"]}],"id":[{"id":"10.13039\/100009619","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021734","name":"Leprosy Research Initiative","doi-asserted-by":"publisher","award":["707.19.62"],"award-info":[{"award-number":["707.19.62"]}],"id":[{"id":"10.13039\/501100021734","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013996","name":"Global Health Innovative Technology","doi-asserted-by":"crossref","award":["G2020-202"],"award-info":[{"award-number":["G2020-202"]}],"id":[{"id":"10.13039\/501100013996","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["www.plosntds.org"],"crossmark-restriction":false},"short-container-title":["PLoS Negl Trop Dis"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Deep learning, which is a part of a broader concept of artificial intelligence (AI) and\/or machine learning has achieved remarkable success in vision tasks. While there is growing interest in the use of this technology in diagnostic support for skin-related neglected tropical diseases (skin NTDs), there have been limited studies in this area and fewer focused on dark skin. In this study, we aimed to develop deep learning based AI models with clinical images we collected for five skin NTDs, namely, Buruli ulcer, leprosy, mycetoma, scabies, and yaws, to understand how diagnostic accuracy can or cannot be improved using different models and training patterns.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Methodology<\/jats:title>\n                    <jats:p>This study used photographs collected prospectively in C\u00f4te d\u2019Ivoire and Ghana through our ongoing studies with use of digital health tools for clinical data documentation and for teledermatology. Our dataset included a total of 1,709 images from 506 patients. Two convolutional neural networks, ResNet-50 and VGG-16 models were adopted to examine the performance of different deep learning architectures and validate their feasibility in diagnosis of the targeted skin NTDs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Principal findings<\/jats:title>\n                    <jats:p>The two models were able to correctly predict over 70% of the diagnoses, and there was a consistent performance improvement with more training samples. The ResNet-50 model performed better than the VGG-16 model. A model trained with PCR confirmed cases of Buruli ulcer yielded 1\u20133% increase in prediction accuracy across all diseases, except, for mycetoma, over a model which training sets included unconfirmed cases.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Our approach was to have the deep learning model distinguish between multiple pathologies simultaneously\u2013which is close to real-world practice. The more images used for training, the more accurate the diagnosis became. The percentages of correct diagnosis increased with PCR-positive cases of Buruli ulcer. This demonstrated that it may be better to input images from the more accurately diagnosed cases in the training models also for achieving better accuracy in the generated AI models. However, the increase was marginal which may be an indication that the accuracy of clinical diagnosis alone is reliable to an extent for Buruli ulcer. Diagnostic tests also have their flaws, and they are not always reliable. One hope for AI is that it will objectively resolve this gap between diagnostic tests and clinical diagnoses with the addition of another tool. While there are still challenges to be overcome, there is a potential for AI to address the unmet needs where access to medical care is limited, like for those affected by skin NTDs.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pntd.0011230","type":"journal-article","created":{"date-parts":[[2023,8,14]],"date-time":"2023-08-14T13:29:06Z","timestamp":1692019746000},"page":"e0011230","update-policy":"https:\/\/doi.org\/10.1371\/journal.pntd.corrections_policy","source":"Crossref","is-referenced-by-count":48,"title":["Deep learning for AI-based diagnosis of skin-related neglected tropical diseases: A pilot study"],"prefix":"10.1371","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9102-1912","authenticated-orcid":true,"given":"Rie R.","family":"Yotsu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengming","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jihun","family":"Hamm","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ronald E.","family":"Blanton","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2023,8,14]]},"reference":[{"key":"pntd.0011230.ref001","doi-asserted-by":"crossref","first-page":"667","DOI":"10.1016\/j.clindermatol.2021.03.012","article-title":"Artifical Intelligence in dermatology for the clinicians","volume":"39","author":"S Patel","year":"2021","journal-title":"Clinics in Dermatology"},{"issue":"7639","key":"pntd.0011230.ref002","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1038\/nature21056","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"A Esteva","year":"2017","journal-title":"Nature"},{"issue":"8","key":"pntd.0011230.ref003","doi-asserted-by":"crossref","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":"HA Haenssle","year":"2018","journal-title":"Ann Oncol"},{"key":"pntd.0011230.ref004","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.ejca.2019.05.023","article-title":"Deep neural networks are superior to dermatologists in melanoma image classification","volume":"119","author":"TJ Brinker","year":"2019","journal-title":"Eur J Cancer"},{"issue":"6","key":"pntd.0011230.ref005","doi-asserted-by":"crossref","first-page":"e466","DOI":"10.1016\/S2589-7500(22)00023-1","article-title":"Artificial intelligence and machine learning algorithms for early detection of skin cancer in community and primary care settings: a systematic review","volume":"4","author":"OT Jones","year":"2022","journal-title":"Lancet Digit Health"},{"issue":"11","key":"pntd.0011230.ref006","doi-asserted-by":"crossref","first-page":"1291","DOI":"10.1001\/jamadermatol.2019.1375","article-title":"Accuracy of Computer-Aided Diagnosis of Melanoma","volume":"155","author":"V Dick","year":"2019","journal-title":"A Meta-analysis. JAMA Dermatol"},{"issue":"11","key":"pntd.0011230.ref007","doi-asserted-by":"crossref","first-page":"1252","DOI":"10.1111\/exd.14022","article-title":"Development and accuracy of an artificial intelligence algorithm for acne grading from smartphone photographs","volume":"28","author":"S Seite","year":"2019","journal-title":"Exp Dermatol"},{"key":"pntd.0011230.ref008","unstructured":"World Health Organization. Ending the neglect to attain the Sustainable Development Goals: a strategic framework for integrated control and management of skin-related neglected tropical diseases. Geneva, Switzerland; 2022. Contract No.: Licence: CC BY-NC-SA 3.0 IGO."},{"issue":"2","key":"pntd.0011230.ref009","first-page":"157","article-title":"WHO strategic framework for integrated control and management of skin-related neglected tropical diseases (skin NTDs)","volume":"188","author":"R Yotsu","year":"2023","journal-title":"What does this mean for dermatologists? British Journal of Dermatology"},{"key":"pntd.0011230.ref010","doi-asserted-by":"crossref","first-page":"e46295","DOI":"10.2196\/46295","article-title":"An mHealth App (eSkinHealth) for Detecting and Managing Skin Diseases in Resource-Limited Settings: Mixed Methods Pilot Study","volume":"6","author":"RR Yotsu","year":"2023","journal-title":"JMIR Dermatol"},{"key":"pntd.0011230.ref011","volume-title":"Deep residual learning for image recognition","author":"K He","year":"2016"},{"issue":"1409","key":"pntd.0011230.ref012","first-page":"1556","article-title":"Very Deep Convolutoinal Networks for Large-scale Image Recognition","author":"K Simonyan","year":"2015","journal-title":"arXiv preprint"},{"key":"pntd.0011230.ref013","volume-title":"Marginalized Latent Sematic Encoder for Zero-Shot Learning","author":"Z Ding","year":"2019"},{"key":"pntd.0011230.ref014","volume-title":"ImageNet: A large-scale hierarchical image database","author":"J Deng","year":"2009"},{"issue":"1","key":"pntd.0011230.ref015","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1186\/s12864-019-6413-7","article-title":"The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation","volume":"21","author":"D Chicco","year":"2020","journal-title":"BMC Genomics"},{"issue":"4","key":"pntd.0011230.ref016","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1002\/wics.101","article-title":"Principal component analysis","volume":"2","author":"H Abdi","year":"2010","journal-title":"Wires Computational Statistics"},{"key":"pntd.0011230.ref017","first-page":"100192","article-title":"Reimagining leprosy elimination with AI analysis of a combination of skin lesion images with demographic and clinical data","volume":"9","author":"RR Barbieri","year":"2022","journal-title":"Lancet Reg Health Am"},{"issue":"6","key":"pntd.0011230.ref018","doi-asserted-by":"crossref","first-page":"827","DOI":"10.1093\/cid\/ciy197","article-title":"Diagnostic Accuracy of Clinical and Microbiological Signs in Patients With Skin Lesions Resembling Buruli Ulcer in an Endemic Region. Clinical infectious diseases: an official publication of the","volume":"67","author":"M Eddyani","year":"2018","journal-title":"Infectious Diseases Society of America"},{"issue":"6","key":"pntd.0011230.ref019","doi-asserted-by":"crossref","first-page":"835","DOI":"10.1093\/cid\/ciy203","article-title":"Diagnostic Tests for Buruli Ulcer: Clinical Judgment Revisited. Clinical infectious diseases: an official publication of the","volume":"67","author":"TS van der Werf","year":"2018","journal-title":"Infectious Diseases Society of America"},{"issue":"1","key":"pntd.0011230.ref020","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1111\/j.1365-3156.2006.01761.x","article-title":"A stepwise approach to the laboratory diagnosis of Buruli ulcer disease","volume":"12","author":"G Bretzel","year":"2007","journal-title":"Trop Med Int Health"},{"issue":"1","key":"pntd.0011230.ref021","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1086\/518604","article-title":"Dry reagent-based polymerase chain reaction compared with other laboratory methods available for the diagnosis of Buruli ulcer disease. Clinical infectious diseases: an official publication of the","volume":"45","author":"V Siegmund","year":"2007","journal-title":"Infectious Diseases Society of America"},{"key":"pntd.0011230.ref022","doi-asserted-by":"crossref","first-page":"8200","DOI":"10.1109\/TIP.2021.3113576","article-title":"Towards Fair Konwledge Transfer for Imbalanced Domain Adaptation","volume":"30","author":"T Jing","year":"2021","journal-title":"IEEE Transactions on Image Processing"},{"issue":"3","key":"pntd.0011230.ref023","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1016\/j.trstmh.2004.05.004","article-title":"Distribution of Buruli ulcer lesions over body surface area in a large case series in Ghana: uncovering clues for mode of transmission","volume":"99","author":"IC Hospers","year":"2005","journal-title":"Trans R Soc Trop Med Hyg"},{"issue":"4","key":"pntd.0011230.ref024","doi-asserted-by":"crossref","first-page":"e0007732","DOI":"10.1371\/journal.pntd.0007732","article-title":"Does skin surface temperature variation account for Buruli ulcer lesion distribution?","volume":"14","author":"NK Sexton-Oates","year":"2020","journal-title":"PLoS Negl Trop Dis"},{"issue":"12","key":"pntd.0011230.ref025","doi-asserted-by":"crossref","first-page":"1236","DOI":"10.36849\/JDD.2020.5545","article-title":"Analysis of Skin Color on the American Academy of Dermatology Public Education Website. Journal of drugs in dermatology","volume":"19","author":"MJ Chang","year":"2020","journal-title":"JDD"},{"issue":"3","key":"pntd.0011230.ref026","doi-asserted-by":"crossref","first-page":"786","DOI":"10.1016\/j.jaad.2020.09.092","article-title":"Demographics of US dermatology residents interested in skin of color: An analysis of website profiles","volume":"85","author":"UK Okoji","year":"2021","journal-title":"J Am Acad Dermatol"}],"updated-by":[{"DOI":"10.1371\/journal.pntd.0011230","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2023,8,24]],"date-time":"2023-08-24T00:00:00Z","timestamp":1692835200000}}],"container-title":["PLOS Neglected Tropical Diseases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pntd.0011230","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T20:20:14Z","timestamp":1702930814000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pntd.0011230"}},"subtitle":[],"editor":[{"given":"Joseph M.","family":"Vinetz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2023,8,14]]},"references-count":26,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2023,8,14]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pntd.0011230","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2023.03.14.23287243","asserted-by":"object"}]},"ISSN":["1935-2735"],"issn-type":[{"value":"1935-2735","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,14]]}}}