{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T03:03:01Z","timestamp":1771556581111,"version":"3.50.1"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T00:00:00Z","timestamp":1771545600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T00:00:00Z","timestamp":1771545600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001652","name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001652","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Virchows Arch"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Psoriasis and eczema are chronic inflammatory skin diseases with overlapping histopathological features, which often lead to diagnostic uncertainty even among experienced dermatopathologists. To address this challenge, we developed a computer-assisted diagnostic framework that combines the Virchow foundation model, pretrained on 1.5 million whole-slide images, with multi-instance learning (MIL) to classify psoriasis and eczema from digitized histopathology slides. Using an internal dataset (\n                    <jats:italic>n<\/jats:italic>\n                    = 40) and an external validation cohort (\n                    <jats:italic>n<\/jats:italic>\n                    = 40), equally balanced between both conditions and annotated by board-certified dermatopathologists, our best-performing configuration (Virchow + CLAM) achieved 85% accuracy, a macro-averaged F1 score of 0.80, and an AUC of 0.81 on the external cohort. This substantially outperformed baseline convolutional neural networks, which reached 61% accuracy, and models relying solely on pretrained feature extractors without MIL, which achieved an average accuracy of 68.8%. In a reader study on the same external cohort, individual dermatopathologist accuracies ranged from 47.5 to 70.0%, with a majority-vote consensus accuracy of 62.5%; our method outperformed both the average individual reader and the consensus under histology-only conditions. Furthermore, the model generates attention heatmaps that provide supportive visual context by highlighting regions associated with model predictions. Importantly, this study is designed as a methodological proof-of-concept conducted under controlled, histology-only conditions and is not intended for direct clinical deployment. Rather than demonstrating clinical readiness, it illustrates the potential of domain-specific foundation models combined with MIL for addressing diagnostically challenging inflammatory dermatoses.\n                  <\/jats:p>","DOI":"10.1007\/s00428-026-04445-x","type":"journal-article","created":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T02:19:22Z","timestamp":1771553962000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Vision transformer-based diagnosis of psoriasis and eczema in whole-slide histology"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8232-8920","authenticated-orcid":false,"given":"Luis Carlos","family":"Rivera Monroy","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anne","family":"Petzold","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Melissa","family":"Sari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Katharina","family":"Breininger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9550-5284","authenticated-orcid":false,"given":"Andreas","family":"Maier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3076-5122","authenticated-orcid":false,"given":"Julio","family":"Vera-Gonzalez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Erdmann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Schliep","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Konstantin","family":"Drexler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dennis","family":"Niebel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stephan","family":"Schreml","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kinan M.","family":"Hayani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Valentin","family":"Aebischer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stephan A.","family":"Braun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paul","family":"Schmidle","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dieter","family":"Metze","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Sticherling","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0229-8931","authenticated-orcid":false,"given":"Carola","family":"Berking","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2005-7533","authenticated-orcid":false,"given":"Elias A. T.","family":"Koch","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4603-1825","authenticated-orcid":false,"given":"Markus V.","family":"Heppt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,20]]},"reference":[{"issue":"2","key":"4445_CR1","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1007\/s12016-012-8305-3","volume":"44","author":"MAN Johnson","year":"2012","unstructured":"Johnson MAN, Armstrong AW (2012) Clinical and histologic diagnostic guidelines for psoriasis: a critical review. Clinical Reviews in Allergy & Immunology 44(2):166\u2013172. https:\/\/doi.org\/10.1007\/s12016-012-8305-3","journal-title":"Clinical Reviews in Allergy & Immunology"},{"issue":"S1","key":"4445_CR2","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/s13555-016-0167-9","volume":"7","author":"CEM Griffiths","year":"2017","unstructured":"Griffiths CEM, Kerkhof P, Czarnecka-Operacz M (2017) Psoriasis and atopic dermatitis. Dermatology and Therapy 7(S1):31\u201341. https:\/\/doi.org\/10.1007\/s13555-016-0167-9","journal-title":"Dermatology and Therapy"},{"issue":"8","key":"4445_CR3","doi-asserted-by":"publisher","first-page":"887","DOI":"10.1001\/jamadermatol.2022.1906","volume":"158","author":"R Elsawi","year":"2022","unstructured":"Elsawi R, Dainty K, Smith Begolka W, Barta K, Butler L, Capozza K et al (2022) The multidimensional burden of atopic dermatitis among adults. JAMA Dermatol 158(8):887. https:\/\/doi.org\/10.1001\/jamadermatol.2022.1906","journal-title":"JAMA Dermatol"},{"issue":"6","key":"4445_CR4","doi-asserted-by":"publisher","first-page":"710","DOI":"10.1684\/ejd.2020.3769","volume":"30","author":"MK An","year":"2020","unstructured":"An MK, Yoon JH, Park EJ, Park HR, Kim KJ, Kim KH (2020) Differential histopathological and immunohistochemical findings between palmar psoriasis and chronic hand eczema. Eur J Dermatol 30(6):710\u2013715. https:\/\/doi.org\/10.1684\/ejd.2020.3769","journal-title":"Eur J Dermatol"},{"issue":"2","key":"4445_CR5","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1007\/s10586-022-03707-y","volume":"26","author":"Z Yu","year":"2022","unstructured":"Yu Z, Wang K, Wan Z, Xie S, Lv Z (2022) Popular deep learning algorithms for disease prediction: a review. Clust Comput 26(2):1231\u20131251. https:\/\/doi.org\/10.1007\/s10586-022-03707-y","journal-title":"Clust Comput"},{"key":"4445_CR6","doi-asserted-by":"publisher","first-page":"1273253","DOI":"10.3389\/fpubh.2023.1273253","volume":"11","author":"M Li","year":"2023","unstructured":"Li M, Jiang Y, Zhang Y, Zhu H (2023) Medical image analysis using deep learning algorithms. Front Public Health 11:1273253. https:\/\/doi.org\/10.3389\/fpubh.2023.1273253","journal-title":"Front Public Health"},{"issue":"18","key":"4445_CR7","doi-asserted-by":"publisher","first-page":"10521","DOI":"10.3390\/app131810521","volume":"13","author":"H Zhang","year":"2023","unstructured":"Zhang H, Qie Y (2023) Applying deep learning to medical imaging: a review. Appl Sci 13(18):10521. https:\/\/doi.org\/10.3390\/app131810521","journal-title":"Appl Sci"},{"key":"4445_CR8","doi-asserted-by":"publisher","unstructured":"Atabansi CC, Nie J, Liu H, Song Q, Yan L, Zhou X (2023) A survey of transformer applications for histopathological image analysis: new developments and future directions. BioMedical Engineering OnLine 22(1). https:\/\/doi.org\/10.1186\/s12938-023-01157-0","DOI":"10.1186\/s12938-023-01157-0"},{"issue":"1","key":"4445_CR9","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1038\/s41598-023-50183-4","volume":"14","author":"BA Schreiber","year":"2024","unstructured":"Schreiber BA, Denholm J, Jaeckle F, Arends MJ, Branson KM, Sch\u00f6nlieb C-B, Soilleux EJ (2024) Rapid artefact removal and H&E-stained tissue segmentation. Sci Rep 14(1):309. https:\/\/doi.org\/10.1038\/s41598-023-50183-4","journal-title":"Sci Rep"},{"key":"4445_CR10","doi-asserted-by":"publisher","unstructured":"Macenko M, Niethammer M, Marron JS, Borland D, Woosley JT, Guan X et al (2009) A method for normalizing histology slides for quantitative analysis. In: 2009 IEEE international symposium on biomedical imaging: From Nano to Macro, pp 1107\u20131110.https:\/\/doi.org\/10.1109\/ISBI.2009.5193250IEEE","DOI":"10.1109\/ISBI.2009.5193250"},{"issue":"4","key":"4445_CR11","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1109\/38.946629","volume":"21","author":"E Reinhard","year":"2001","unstructured":"Reinhard E, Adhikhmin M, Gooch B, Shirley P (2001) Color transfer between images. IEEE Comput Graphics Appl 21(4):34\u201341. https:\/\/doi.org\/10.1109\/38.946629","journal-title":"IEEE Comput Graphics Appl"},{"issue":"8","key":"4445_CR12","doi-asserted-by":"publisher","first-page":"1962","DOI":"10.1109\/TMI.2016.2529665","volume":"35","author":"A Vahadane","year":"2016","unstructured":"Vahadane A, Peng T, Sethi A, Albarqouni S, Wang L, Baust M et al (2016) Structure-preserving color normalization and sparse stain separation for histological images. IEEE Trans Med Imaging 35(8):1962\u20131971. https:\/\/doi.org\/10.1109\/TMI.2016.2529665","journal-title":"IEEE Trans Med Imaging"},{"key":"4445_CR13","doi-asserted-by":"publisher","unstructured":"Zingman I, Frayle S, Tankoyeu I, Sukhanov S, Heinemann F (2023) A comparative evaluation of image-to-image translation methods for stain transfer in histopathology. https:\/\/doi.org\/10.48550\/arXiv.2303.17009","DOI":"10.48550\/arXiv.2303.17009"},{"key":"4445_CR14","doi-asserted-by":"publisher","unstructured":"Wang X, Yang S, Zhang J, Wang M, Zhang J, Yang W et al (2022) Transformer-based unsupervised contrastive learning for histopathological image classification. Med Image Anal 81:102559. https:\/\/doi.org\/10.1016\/j.media.2022.102559","DOI":"10.1016\/j.media.2022.102559"},{"key":"4445_CR15","doi-asserted-by":"publisher","DOI":"10.1101\/2023.07.21.23292757","author":"A Filiot","year":"2023","unstructured":"Filiot A, Ghermi R, Olivier A, Jacob P, Fidon L, Camara A, Mac Kain A, Saillard C, Schiratti J-B (2023). Scaling self-Supervised Learning for histopathology with Masked Image Modeling. https:\/\/doi.org\/10.1101\/2023.07.21.23292757","journal-title":"Scaling self-Supervised Learning for histopathology with Masked Image Modeling"},{"key":"4445_CR16","doi-asserted-by":"publisher","unstructured":"Chen RJ, Ding T, Lu MY, Williamson DFK, Jaume G, Song AH et al (2024) Towards a general-purpose foundation model for computational pathology. Nat Med 30(3):850\u2013862. https:\/\/doi.org\/10.1038\/s41591-024-02857-3","DOI":"10.1038\/s41591-024-02857-3"},{"key":"4445_CR17","doi-asserted-by":"publisher","unstructured":"Vorontsov E, Bozkurt A, Casson A, Shaikovski G, Zelechowski M, Liu S et al (2023) Virchow: a million-slide digital pathology foundation model. https:\/\/doi.org\/10.48550\/arXiv.2309.07778","DOI":"10.48550\/arXiv.2309.07778"},{"key":"4445_CR18","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition.https:\/\/doi.org\/10.48550\/arXiv.1512.03385","DOI":"10.48550\/arXiv.1512.03385"},{"key":"4445_CR19","doi-asserted-by":"publisher","unstructured":"Chollet F (2016) Xception: deep learning with depthwise separable convolutions. https:\/\/doi.org\/10.1109\/CVPR.2017.195","DOI":"10.1109\/CVPR.2017.195"},{"key":"4445_CR20","doi-asserted-by":"publisher","unstructured":"Howard A, Sandler M, Chu G, Chen L-C, Chen B, Tan M et al (2019) Searching for MobileNetV3. https:\/\/doi.org\/10.48550\/arXiv.1905.02244","DOI":"10.48550\/arXiv.1905.02244"},{"key":"4445_CR21","doi-asserted-by":"publisher","unstructured":"Huang G, Liu Z, Maaten L, Weinberger KQ (2016) Densely connected convolutional networks. https:\/\/doi.org\/10.48550\/arXiv.1608.06993","DOI":"10.48550\/arXiv.1608.06993"},{"issue":"100377","key":"4445_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpi.2024.100377","volume":"15","author":"K DeVoe","year":"2024","unstructured":"DeVoe K, Takahashi G, Tarshizi E, Sacker A (2024) Evaluation of the precision and accuracy in the classification of breast histopathology images using the MobileNetV3 model. J Pathol Inform 15(100377):100377. https:\/\/doi.org\/10.1016\/j.jpi.2024.100377","journal-title":"J Pathol Inform"},{"key":"4445_CR23","doi-asserted-by":"publisher","unstructured":"Girdhar N, Sinha A, Gupta S (2022) DenseNet-II: an improved deep convolutional neural network for melanoma cancer detection. Soft Comput, 1\u201320. https:\/\/doi.org\/10.1007\/s00500-022-07406-z","DOI":"10.1007\/s00500-022-07406-z"},{"key":"4445_CR24","doi-asserted-by":"publisher","unstructured":"Ilse M, Tomczak JM, Welling M (2018) Attention-based deep multiple instance learning. https:\/\/doi.org\/10.48550\/arXiv.1802.04712","DOI":"10.48550\/arXiv.1802.04712"},{"issue":"6","key":"4445_CR25","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1038\/s41551-020-00682-w","volume":"5","author":"MY Lu","year":"2021","unstructured":"Lu MY, Williamson DFK, Chen TY, Chen RJ, Barbieri M, Mahmood F (2021) Data-efficient and weakly supervised computational pathology on whole-slide images. Nature Biomedical Engineering 5(6):555\u2013570. https:\/\/doi.org\/10.1038\/s41551-020-00682-w","journal-title":"Nature Biomedical Engineering"},{"issue":"9","key":"4445_CR26","doi-asserted-by":"publisher","first-page":"1650","DOI":"10.1016\/j.ccell.2023.08.002","volume":"41","author":"SJ Wagner","year":"2023","unstructured":"Wagner SJ, Reisenb\u00fcchler D, West NP, Niehues JM, Zhu J, Foersch S et al (2023) Transformer-based biomarker prediction from colorectal cancer histology: a large-scale multicentric study. Cancer Cell 41(9):1650\u201316614. https:\/\/doi.org\/10.1016\/j.ccell.2023.08.002","journal-title":"Cancer Cell"},{"key":"4445_CR27","doi-asserted-by":"publisher","DOI":"10.1007\/s00428-025-04272-6","author":"A Petzold","year":"2025","unstructured":"Petzold A, Wessely A, Erdmann M, Schliep S, Schreml S, Rivera Monroy LC et al (2025) An artificial intelligence model of whole-slide pathology specimens differentiating cutaneous high-grade squamous proliferations. Virchows Arch. https:\/\/doi.org\/10.1007\/s00428-025-04272-6","journal-title":"Virchows Arch"}],"container-title":["Virchows Archiv"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00428-026-04445-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00428-026-04445-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00428-026-04445-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T02:19:24Z","timestamp":1771553964000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00428-026-04445-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,20]]},"references-count":27,"alternative-id":["4445"],"URL":"https:\/\/doi.org\/10.1007\/s00428-026-04445-x","relation":{},"ISSN":["0945-6317","1432-2307"],"issn-type":[{"value":"0945-6317","type":"print"},{"value":"1432-2307","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,20]]},"assertion":[{"value":"4 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 January 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 February 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 February 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study was approved by an independent research ethics committee of the Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg (FAU; approval number 22-368-Br) and was conducted following the principles of the Helsinki Declaration in its current version.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare a potential competing interest related to another manuscript recently published on Virchows Archive. The related publication, titled \u201cAn artificial intelligence model of whole-slide pathology specimens differentiating cutaneous high-grade squamous proliferations\u201d addresses overlapping methodologies and applications in the field of artificial intelligence and pathology. While the current manuscript and the related project focus on distinct research questions and datasets, there is potential conceptual overlap. The authors affirm that all efforts have been made to ensure transparency and avoid conflicts of interest.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}