{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,10]],"date-time":"2026-11-10T17:54:51Z","timestamp":1794333291537,"version":"4.9.0"},"reference-count":23,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T00:00:00Z","timestamp":1743552000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec><jats:title>Objective<\/jats:title><jats:p>To improve and validate a convolutional neural network (CNN)-based model for the automated scoring of nail psoriasis severity using the modified Nail Psoriasis Severity Index (mNAPSI) with adequate accuracy across all severity classes and without dependency on standardized conditions.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>Patients with psoriasis (PsO), psoriatic arthritis (PsA), and non-psoriatic controls including healthy individuals and patients with rheumatoid arthritis were included for training, while validation utilized an independent cohort of psoriatic patients. Nail photographs were pre-processed and segmented and mNAPSI scores were annotated by five expert readers. A CNN based on Bidirectional Encoder representation from Image Transformers (BEiT) architecture and pre-trained on ImageNet-22k was fine-tuned for mNAPSI classification. Model performance was compared with human annotations by using area under the receiver operating characteristic curve (AUROC) and other metrics. A reader study was performed to assess inter-rater variability.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>In total, 460 patients providing 4,400 nail photographs were included in the training dataset. The independent validation dataset included 118 further patients who provided 929 nail photographs. The CNN demonstrated high classification performance on the training dataset, achieving mean (SD) AUROC of 86% \u00b1\u202f7% across mNAPSI classes. Performance remained robust on the independent validation dataset, with a mean AUROC of 80% \u00b1 9%, despite variability in imaging conditions. Compared with human annotation, the CNN achieved a Pearson correlation of 0.94 on a patient-level, which remained consistent in the validation dataset.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>We developed and validated a CNN that enables the automated, objective scoring of nail psoriasis severity based on mNAPSI with high reliability and without need of image standardization. This approach has potential clinical utility for enabling a standardized time-efficient assessment of nail involvement in the psoriatic disease and possibly as a self-reporting tool.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fmed.2025.1574413","type":"journal-article","created":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T06:58:34Z","timestamp":1743577114000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Advancement and independent validation of a deep learning-based tool for automated scoring of nail psoriasis severity using the modified nail psoriasis severity index"],"prefix":"10.3389","volume":"12","author":[{"given":"Stephan","family":"Kemenes","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liu","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maja","family":"Schlereth","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rita","family":"Noversa de Sousa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ioanna","family":"Minopoulou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pauline","family":"Fenzl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giulia","family":"Corte","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Melek","family":"Yalcin Mutlu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael Wolfgang","family":"H\u00f6ner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ioannis","family":"Sagonas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Birte","family":"Coppers","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anna-Maria","family":"Liphardt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Simon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arnd","family":"Kleyer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lukas","family":"Folle","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Sticherling","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Georg","family":"Schett","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Maier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Filippo","family":"Fagni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,4,2]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"16095","DOI":"10.3390\/ijms242216095","article-title":"Inflammation and psoriasis: a comprehensive review","volume":"24","author":"Man","year":"2023","journal-title":"Int J Mol Sci"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1038\/s41584-022-00776-6","article-title":"Psoriatic arthritis from a mechanistic perspective","volume":"18","author":"Schett","year":"2022","journal-title":"Nat Rev Rheumatol"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1590\/abd1806-4841.20142633","article-title":"Nail psoriasis: a review of the literature","volume":"89","author":"Schons","year":"2014","journal-title":"An Bras Dermatol"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1111\/1756-185X.14442","article-title":"The impact of nail psoriasis on disease activity, quality of life, and clinical variables in patients with psoriatic arthritis: a cross-sectional multicenter study","volume":"26","author":"Cengiz","year":"2023","journal-title":"Int J Rheum Dis"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1111\/bjd.13272","article-title":"Nail involvement as a predictor of concomitant psoriatic arthritis in patients with psoriasis","volume":"171","author":"Langenbruch","year":"2014","journal-title":"Br J Dermatol"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1067\/S0190-9622(03)00910-1","article-title":"Nail psoriasis severity index: a useful tool for evaluation of nail psoriasis","volume":"49","author":"Rich","year":"2003","journal-title":"J Am Acad Dermatol"},{"key":"ref7","first-page":"123","article-title":"The modified nail psoriasis severity index: validation of an instrument to assess psoriatic nail involvement in patients with psoriatic arthritis","volume":"34","author":"Cassell","year":"2007","journal-title":"J Rheumatol"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1111\/bjd.15831","article-title":"Reporting of outcomes in randomized controlled trials on nail psoriasis: a systematic review","volume":"178","author":"Busard","year":"2018","journal-title":"Br J Dermatol"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1186\/s13075-023-03138-z","article-title":"Nail psoriasis dynamics during biologic treatment and withdrawal in patients with psoriasis who may be at high risk of developing psoriatic arthritis: a post hoc analysis of the VOYAGE 2 randomized trial","volume":"25","author":"Tillett","year":"2023","journal-title":"Arthritis Res Ther"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"105300","DOI":"10.1016\/j.compbiomed.2022.105300","article-title":"A mask R-CNN based automatic assessment system for nail psoriasis severity","volume":"143","author":"Hsieh","year":"2022","journal-title":"Comput Biol Med"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"1310","DOI":"10.1111\/1346-8138.17313","article-title":"Automatic evaluation of nail psoriasis severity index using deep learning algorithm","volume":"51","author":"Paik","year":"2024","journal-title":"J Dermatol"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"5329","DOI":"10.1038\/s41598-023-32440-8","article-title":"DeepNAPSI multi-reader nail psoriasis prediction using deep learning","volume":"13","author":"Folle","year":"2023","journal-title":"Sci Rep"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"2665","DOI":"10.1002\/art.21972","article-title":"Classification criteria for psoriatic arthritis: development of new criteria from a large international study","volume":"54","author":"Taylor","year":"2006","journal-title":"Arthritis Rheum"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"vi5-9","DOI":"10.1093\/rheumatology\/kes279","article-title":"ACR\/EULAR 2010 rheumatoid arthritis classification criteria","volume":"51","author":"Kay","year":"2012","journal-title":"Rheumatology"},{"key":"ref15","article-title":"Mediapipe: A framework for perceiving and processing reality","author":"Lugaresi","year":"2019"},{"key":"ref16","article-title":"BEiT: BERT pre-training of image transformers","author":"Bao","year":"2021","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"850552","DOI":"10.3389\/fmed.2022.850552","article-title":"Deep learning-based classification of inflammatory arthritis by identification of joint shape patterns-how neural networks can tell us where to \u201cdeep dive\u201d clinically","volume":"9","author":"Folle","year":"2022","journal-title":"Front Med"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1007\/s00256-021-03830-8","article-title":"Artificial intelligence for MRI diagnosis of joints: a scoping review of the current state-of-the-art of deep learning-based approaches","volume":"51","author":"Fritz","year":"2022","journal-title":"Skeletal Radiol"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1297088","DOI":"10.3389\/fmed.2024.1297088","article-title":"Artificial intelligence model for segmentation and severity scoring of osteophytes in hand osteoarthritis on ultrasound images","volume":"11","author":"Overgaard","year":"2024","journal-title":"Front Med"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"e000891","DOI":"10.1136\/rmdopen-2018-000891","article-title":"Neural networks for automatic scoring of arthritis disease activity on ultrasound images","volume":"5","author":"Andersen","year":"2019","journal-title":"RMD Open"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"1355","DOI":"10.3390\/biomedicines10061355","article-title":"Deep learning-based computer-aided diagnosis of rheumatoid arthritis with hand X-ray images conforming to modified Total sharp\/van der Heijde score","volume":"10","author":"Wang","year":"2022","journal-title":"Biomedicines"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"e004273","DOI":"10.1136\/rmdopen-2024-004273","article-title":"Deep learning-based classification of erosion, synovitis and osteitis in hand MRI of patients with inflammatory arthritis","volume":"10","author":"Schlereth","year":"2024","journal-title":"RMD Open"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1038\/s41540-024-00458-x","article-title":"Reliable and easy-to-use calculating tool for the nail psoriasis severity index using deep learning","volume":"10","author":"Horikawa","year":"2024","journal-title":"NPJ Syst Biol Appl"}],"updated-by":[{"DOI":"10.3389\/fmed.2025.1617441","type":"corrigendum","label":"Corrigendum","source":"publisher","updated":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T00:00:00Z","timestamp":1749081600000}}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1574413\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T17:07:29Z","timestamp":1749056849000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1574413\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,2]]},"references-count":23,"alternative-id":["10.3389\/fmed.2025.1574413"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2025.1574413","relation":{"corrigendum":[{"id-type":"doi","id":"10.3389\/fmed.2025.1617441","asserted-by":"object"}],"has-part":[{"id-type":"doi","id":"https:\/\/doi.org\/10.3389\/fmed.2025.1574413.s001","asserted-by":"subject"},{"id-type":"doi","id":"https:\/\/doi.org\/10.3389\/fmed.2025.1574413.s002","asserted-by":"subject"},{"id-type":"doi","id":"https:\/\/doi.org\/10.3389\/fmed.2025.1574413.s003","asserted-by":"subject"},{"id-type":"doi","id":"https:\/\/doi.org\/10.3389\/fmed.2025.1574413.s004","asserted-by":"subject"}]},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,2]]},"article-number":"1574413"}}