{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T04:11:59Z","timestamp":1751343119289,"version":"3.41.0"},"reference-count":31,"publisher":"Public Library of Science (PLoS)","issue":"6","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Granulomatous rosacea (GR) and lupus miliaris disseminatus faciei (LMDF) exhibit overlapping clinical features, making their differentiation challenging. While histopathological examination remains the gold standard, it is invasive and time-consuming, highlighting the need for non-invasive diagnostic approaches. This study evaluates artificial intelligence (AI)-based models for differentiating between GR and LMDF and assess their impact on clinician performance. This retrospective pilot study included 96 patients (62 GR, 34 LMDF) with histopathologically confirmed diagnoses. Neural network models, including convolutional neural networks and vision transformers (ViT), were applied to cropped lesion images while a transformer-based multiple instance learning (TransMIL) approach was used for whole-image analysis. Diagnostic accuracy was also compared between clinicians with and without AI assistance. ViT_base_patch16_224 achieved the highest accuracy (93.0%) and reliability (\u03ba\u2009=\u20090.81) on cropped images, while the TransMIL reached 70% accuracy on whole images. AI augmentation significantly improved clinicians\u2019 diagnostic accuracy from 64.7% to 70.3% (<jats:italic>p<\/jats:italic>\u2009=\u20090.0136), with the greatest improvement observed among general practitioners. Additionally, mean diagnostic time decreased from 10.7 to 6.4 minutes. These findings highlight the potential of AI models, particularly ViT, in facilitating the differential diagnosis of GR and LMDF. AI-augmented diagnosis improved accuracy and efficiency across all clinician expertise levels, supporting its integration as a complementary tool in dermatological practice.<\/jats:p>","DOI":"10.1371\/journal.pone.0326763","type":"journal-article","created":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T17:42:38Z","timestamp":1751305358000},"page":"e0326763","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["AI-augmented differential diagnosis of granulomatous rosacea and lupus miliaris disseminatus faciei: A 23\u2013year retrospective pilot study"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6253-3094","authenticated-orcid":true,"given":"Sang-Hoon","family":"Lee","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyun","family":"Kang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seung-Phil","family":"Hong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eung Ho","family":"Choi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joong","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8121-8399","authenticated-orcid":true,"given":"Minseob","family":"Eom","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2025,6,30]]},"reference":[{"issue":"4","key":"pone.0326763.ref001","doi-asserted-by":"crossref","first-page":"584","DOI":"10.1067\/mjd.2002.120625","article-title":"Standard classification of rosacea: report of the national rosacea society expert committee on the classification and staging of Rosacea","volume":"46","author":"J Wilkin","year":"2002","journal-title":"J Am Acad Dermatol"},{"issue":"2","key":"pone.0326763.ref002","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1159\/000068457","article-title":"Lupus miliaris disseminatus faciei: a distinctive rosacea-like syndrome and not a granulomatous form of rosacea","volume":"206","author":"MR van de Scheur","year":"2003","journal-title":"Dermatology"},{"issue":"11","key":"pone.0326763.ref003","doi-asserted-by":"crossref","first-page":"819","DOI":"10.1097\/DAD.0000000000001243","article-title":"Granulomatous Rosacea Versus Lupus Miliaris Disseminatus Faciei-2 Faces of Facial Granulomatous Disorder: A Clinicohistological and Molecular Study","volume":"40","author":"A Chougule","year":"2018","journal-title":"Am J Dermatopathol"},{"issue":"3","key":"pone.0326763.ref004","doi-asserted-by":"crossref","DOI":"10.1016\/j.jaad.2004.03.030","article-title":"Rosacea: I. Etiology, pathogenesis, and subtype classification","volume":"51","author":"GH Crawford","year":"2004","journal-title":"J Am Acad Dermatol"},{"issue":"5","key":"pone.0326763.ref005","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1111\/cup.14796","article-title":"Clinical and Histopathological Insights Into Lupus Miliaris Disseminatus Faciei: A Review of 70 Cases","volume":"52","author":"M Nasimi","year":"2025","journal-title":"J Cutan Pathol"},{"issue":"4","key":"pone.0326763.ref006","doi-asserted-by":"crossref","first-page":"614","DOI":"10.1111\/j.1365-2133.1997.tb03797.x","article-title":"Lupus miliaris disseminatus faciei--the DNA of Mycobacterium tuberculosis is not detectable in active lesions by polymerase chain reaction","volume":"137","author":"E Hodak","year":"1997","journal-title":"Br J Dermatol"},{"issue":"1","key":"pone.0326763.ref007","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1007\/s13555-014-0066-x","article-title":"Lewandowsky\u2019s Rosaceiform Eruption: a Form of Cutaneous Tuberculosis Confirmed by PCR in two patients","volume":"5","author":"R Conlledo","year":"2015","journal-title":"Dermatol Ther (Heidelb)"},{"issue":"1","key":"pone.0326763.ref008","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1097\/00000372-200102000-00002","article-title":"Facial granulomatous diseases: a study of four cases tested for the presence of Mycobacterium tuberculosis DNA using nested polymerase chain reaction","volume":"23","author":"G Ferrara","year":"2001","journal-title":"Am J Dermatopathol"},{"issue":"8","key":"pone.0326763.ref009","doi-asserted-by":"crossref","first-page":"1504","DOI":"10.1016\/j.jid.2020.02.026","article-title":"Artificial Intelligence in Dermatology: A Primer","volume":"140","author":"AT Young","year":"2020","journal-title":"J Invest Dermatol"},{"issue":"6","key":"pone.0326763.ref010","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":"3","key":"pone.0326763.ref011","doi-asserted-by":"crossref","DOI":"10.2196\/23415","article-title":"A novel convolutional neural network for the diagnosis and classification of Rosacea: Usability Study","volume":"9","author":"Z Zhao","year":"2021","journal-title":"JMIR Med Inform"},{"key":"pone.0326763.ref012","volume-title":"Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"K He","year":"2016"},{"key":"pone.0326763.ref013","first-page":"27","volume-title":"Rethinking the Inception Architecture for Computer Vision. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"C Szegedy","year":"2016"},{"key":"pone.0326763.ref014","doi-asserted-by":"crossref","unstructured":"Chollet F. Xception: Deep Learning with Depthwise Separable Convolutions. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017.","DOI":"10.1109\/CVPR.2017.195"},{"key":"pone.0326763.ref015","volume-title":"Densely Connected Convolutional Networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"G Huang","year":"2017"},{"key":"pone.0326763.ref016","first-page":"6105","article-title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks.","volume-title":"Proceedings of the 36th International Conference on Machine Learning; Proceedings of Machine Learning Research","author":"M Tan","year":"2019"},{"key":"pone.0326763.ref017","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"A Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"pone.0326763.ref018","unstructured":"Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L. 2009 IEEE conference on computer vision and pattern recognition. In: IEEE conference on computer vision and pattern recognition. 2009."},{"issue":"1","key":"pone.0326763.ref019","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1007\/s10479-005-5724-z","article-title":"A Tutorial on the Cross-Entropy Method","volume":"134","author":"P-T de Boer","year":"2005","journal-title":"Ann Oper Res"},{"key":"pone.0326763.ref020","unstructured":"Kingma DP. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980. 2014."},{"key":"pone.0326763.ref021","doi-asserted-by":"crossref","unstructured":"Al-Kababji A, Bensaali F, Dakua SP. Scheduling techniques for liver segmentation: Reducelronplateau vs onecyclelr. In: International Conference on Intelligent Systems and Pattern Recognition. 2022.","DOI":"10.1007\/978-3-031-08277-1_17"},{"key":"pone.0326763.ref022","first-page":"2136","article-title":"Transmil: Transformer based correlated multiple instance learning for whole slide image classification","volume":"34","author":"Z Shao","year":"2021","journal-title":"Adv Neural Information Processing Syst"},{"key":"pone.0326763.ref023","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/j.artint.2013.06.003","article-title":"Multiple instance classification: Review, taxonomy and comparative study","volume":"201","author":"J Amores","year":"2013","journal-title":"Artificial Intelligence"},{"key":"pone.0326763.ref024","volume-title":"Attention-based deep multiple instance learning. International conference on machine learning","author":"M Ilse","year":"2018"},{"issue":"3","key":"pone.0326763.ref025","doi-asserted-by":"crossref","first-page":"276","DOI":"10.11613\/BM.2012.031","article-title":"Interrater reliability: the kappa statistic","volume":"22","author":"ML McHugh","year":"2012","journal-title":"Biochem Med (Zagreb)"},{"issue":"7","key":"pone.0326763.ref026","doi-asserted-by":"crossref","first-page":"3447","DOI":"10.3390\/s23073447","article-title":"PLG-ViT: Vision Transformer with Parallel Local and Global Self-Attention","volume":"23","author":"N Ebert","year":"2023","journal-title":"Sensors (Basel)"},{"key":"pone.0326763.ref027","doi-asserted-by":"crossref","first-page":"103000","DOI":"10.1016\/j.media.2023.103000","article-title":"Advances in medical image analysis with vision Transformers: A comprehensive review","volume":"91","author":"R Azad","year":"2024","journal-title":"Med Image Anal"},{"issue":"27","key":"pone.0326763.ref028","article-title":"Demodex-induced Lupus miliaris disseminatus faciei: A case report","volume":"99","author":"Y Luo","year":"2020","journal-title":"Medicine (Baltimore)"},{"issue":"9","key":"pone.0326763.ref029","first-page":"864","article-title":"Nosology and therapeutic options for lupus miliaris disseminatus faciei","volume":"38","author":"N Al-Mutairi","year":"2011","journal-title":"J Dermatol"},{"issue":"3","key":"pone.0326763.ref030","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1159\/000099595","article-title":"Lupus miliaris disseminatus faciei associated with epidermal cysts","volume":"214","author":"A Watabe","year":"2007","journal-title":"Dermatology"},{"issue":"4","key":"pone.0326763.ref031","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1111\/1346-8138.12773","article-title":"The detection of Propionibacterium acnes signatures in granulomas of lupus miliaris disseminatus faciei","volume":"42","author":"J Nishimoto","year":"2015","journal-title":"J Dermatol"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0326763","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T17:42:49Z","timestamp":1751305369000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0326763"}},"subtitle":[],"editor":[{"given":"Aneesh","family":"Basheer","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":31,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,6,30]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0326763","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,30]]}}}