{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T11:47:38Z","timestamp":1782128858787,"version":"3.54.5"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T00:00:00Z","timestamp":1781740800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T00:00:00Z","timestamp":1782086400000},"content-version":"vor","delay-in-days":4,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100010447","name":"German Center for Cardiovascular Research","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100010447","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001674","name":"Fondation Leducq","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001674","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005971","name":"Deutsche Herzstiftung","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005971","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007601","name":"Horizon 2020","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007601","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The integration of multi-stain histopathology images through deep learning poses a significant challenge. Current approaches struggle with data heterogeneity and missing data, as concatenating multi-stain features may not effectively model stain-specific and cross-stain interactions. We introduce UNICORN (UNiversal stain Integration network for CORonary classificatioN), a two-stage, end-to-end trainable model comprising transformer self-attention blocks to process multi-stain histopathology for atherosclerosis severity prediction. The initial stage employs domain-specific expert models to extract features from each staining. An aggregation expert model then integrates features by learning their interactions. On a multi-class, multi-stain whole slide images (WSIs) dataset of atherosclerotic lesions from Munich Cardiovascular Studies Biobank (MISSION), UNICORN achieved a classification accuracy of 0.68, significantly outperforming state-of-the-art models. UNICORN identifies relevant tissue phenotypes across stainings and implicitly models disease progression. Its explainability and effectiveness in predicting atherosclerosis progression highlight the potential for broader applications in medical research and decision support.<\/jats:p>","DOI":"10.1038\/s41746-026-02829-6","type":"journal-article","created":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T11:09:54Z","timestamp":1781780994000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["UNICORN: a deep learning model for integrating multi-stain data in histopathology"],"prefix":"10.1038","volume":"9","author":[{"given":"Valentin","family":"Koch","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sabine","family":"Bauer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shweta","family":"Mahajan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Valerio","family":"Lupperger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Joner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heribert","family":"Schunkert","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julia A.","family":"Schnabel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Moritz","family":"von Scheidt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carsten","family":"Marr","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,18]]},"reference":[{"key":"2829_CR1","doi-asserted-by":"publisher","first-page":"1355","DOI":"10.1161\/01.CIR.92.5.1355","volume":"92","author":"HC Stary","year":"1995","unstructured":"Stary, H. C. et al. A definition of advanced types of atherosclerotic lesions and a histological classification of atherosclerosis. A report from the Committee on Vascular Lesions of the Council on Arteriosclerosis, American Heart Association. Circulation 92, 1355\u20131374 (1995).","journal-title":"Circulation"},{"key":"2829_CR2","doi-asserted-by":"publisher","first-page":"2462","DOI":"10.1161\/01.CIR.89.5.2462","volume":"89","author":"HC Stary","year":"1994","unstructured":"Stary, H. C. et al. A definition of initial, fatty streak, and intermediate lesions of atherosclerosis. A report from the Committee on Vascular Lesions of the Council on Arteriosclerosis, American Heart Association. Circulation 89, 2462\u20132478 (1994).","journal-title":"Circulation"},{"key":"2829_CR3","doi-asserted-by":"publisher","first-page":"1262","DOI":"10.1161\/01.ATV.20.5.1262","volume":"20","author":"R Virmani","year":"2000","unstructured":"Virmani, R., Kolodgie, F. D., Burke, A. P., Farb, A. & Schwartz, S. M. Lessons from sudden coronary death: a comprehensive morphological classification scheme for atherosclerotic lesions. Arterioscler. Thromb. Vasc. Biol. 20, 1262\u20131275 (2000).","journal-title":"Arterioscler. Thromb. Vasc. Biol."},{"key":"2829_CR4","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1038\/nrcardio.2014.62","volume":"11","author":"F Otsuka","year":"2014","unstructured":"Otsuka, F., Joner, M., Prati, F., Virmani, R. & Narula, J. Clinical classification of plaque morphology in coronary disease. Nat. Rev. Cardiol. 11, 379\u2013389 (2014).","journal-title":"Nat. Rev. Cardiol."},{"key":"2829_CR5","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1161\/CIRCULATIONAHA.123.065657","volume":"149","author":"C Onnis","year":"2024","unstructured":"Onnis, C. et al. Coronary artery calcification: current concepts and clinical implications. Circulation 149, 251\u2013266 (2024).","journal-title":"Circulation"},{"key":"2829_CR6","doi-asserted-by":"publisher","first-page":"286","DOI":"10.4070\/kcj.2021.0999","volume":"51","author":"HY Lee","year":"2021","unstructured":"Lee, H. Y., Lim, S. & Park, S. Erratum: Role of inflammation in arterial calcification. Korean Circ. J. 51, 286\u2013287 (2021).","journal-title":"Korean Circ. J."},{"key":"2829_CR7","volume":"1","author":"N Kassis","year":"2022","unstructured":"Kassis, N. et al. Fibrous cap thickness predicts stable coronary plaque progression: early clinical validation of a semiautomated OCT technology. Catheter. Cardiovasc. Interv. 1, 100400 (2022).","journal-title":"Catheter. Cardiovasc. Interv."},{"key":"2829_CR8","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1097\/PAI.0b013e3181a60898","volume":"17","author":"AS-Y Leong","year":"2009","unstructured":"Leong, A. S.-Y. Quantitative immunohistology: tissue section thickness, another glitch in the path to standardization. Appl. Immunohistochem. Mol. Morphol. 17, 465\u2013469 (2009).","journal-title":"Appl. Immunohistochem. Mol. Morphol."},{"key":"2829_CR9","doi-asserted-by":"publisher","first-page":"411","DOI":"10.4132\/jptm.2016.08.08","volume":"50","author":"S-W Kim","year":"2016","unstructured":"Kim, S.-W., Roh, J. & Park, C.-S. Immunohistochemistry for pathologists: protocols, pitfalls, and tips. J Pathol Transl Med 50, 411\u2013418 (2016).","journal-title":"J Pathol Transl Med"},{"key":"2829_CR10","doi-asserted-by":"crossref","unstructured":"Jones, M. L., Bancroft, J. D. & Gamble, M. in Theory and Practice of Histological Techniques (Sixth Edition) (eds. Bancroft, J. D. & Gamble, M.) 135\u2013160 (Churchill Livingstone, Edinburgh, 2008).","DOI":"10.1016\/B978-0-443-10279-0.50017-8"},{"key":"2829_CR11","doi-asserted-by":"publisher","first-page":"1650","DOI":"10.1016\/j.ccell.2023.08.002","volume":"41","author":"SJ Wagner","year":"2023","unstructured":"Wagner, S. J. et al. Transformer-based biomarker prediction from colorectal cancer histology: a large-scale multicentric study. Cancer Cell 41, 1650\u20131661.e4 (2023).","journal-title":"Cancer Cell"},{"key":"2829_CR12","doi-asserted-by":"publisher","first-page":"775","DOI":"10.1038\/s41591-021-01343-4","volume":"27","author":"J van der Laak","year":"2021","unstructured":"van der Laak, J., Litjens, G. & Ciompi, F. Deep learning in histopathology: the path to the clinic. Nat. Med. 27, 775\u2013784 (2021).","journal-title":"Nat. Med."},{"key":"2829_CR13","doi-asserted-by":"crossref","unstructured":"Chen, R. J. et al. Scaling vision transformers to gigapixel images via hierarchical self-supervised learning. in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 16144\u201316155 (2022).","DOI":"10.1109\/CVPR52688.2022.01567"},{"key":"2829_CR14","doi-asserted-by":"publisher","first-page":"841","DOI":"10.1109\/TBME.2009.2035102","volume":"57","author":"Y Al-Kofahi","year":"2010","unstructured":"Al-Kofahi, Y., Lassoued, W., Lee, W. & Roysam, B. Improved automatic detection and segmentation of cell nuclei in histopathology images. IEEE Trans. Biomed. Eng. 57, 841\u2013852 (2010).","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"2829_CR15","unstructured":"Ilse, M., Tomczak, J. & Welling, M. Attention-based deep multiple instance learning. in Proceedings of the 35th International Conference on Machine Learning (eds. Dy, J. & Krause, A.) Vol. 80, 2127\u20132136 (PMLR, 10\u201315 Jul 2018)."},{"key":"2829_CR16","unstructured":"Shao, Z. et al. Transmil: Transformer based correlated multiple instance learning for whole slide image classification. Adv. Neural Inf. Process. Syst. https:\/\/arxiv.org\/abs\/2106.00908 (2021)."},{"key":"2829_CR17","unstructured":"Vorontsov, E. et al. Virchow: a million-slide digital pathology foundation model. https:\/\/arxiv.org\/abs\/2309.07778 (2023)."},{"key":"2829_CR18","unstructured":"Chen, R. J. et al. A general-purpose self-supervised model for computational pathology. https:\/\/arxiv.org\/abs\/2308.15474 (2023)."},{"key":"2829_CR19","unstructured":"Campanella, G. et al. Computational pathology at health system scale\u2014self-supervised foundation models from three billion images. https:\/\/arxiv.org\/abs\/2310.07033 (2023)."},{"key":"2829_CR20","doi-asserted-by":"publisher","DOI":"10.3389\/fcvm.2021.779807","volume":"8","author":"O Holmberg","year":"2021","unstructured":"Holmberg, O. et al. Histopathology-based deep-learning predicts atherosclerotic lesions in intravascular imaging. Front. Cardiovasc. Med. 8, 779807 (2021).","journal-title":"Front. Cardiovasc. Med."},{"key":"2829_CR21","doi-asserted-by":"crossref","unstructured":"Murray, J. M., Pfeffer, P., Seifert, R. & Hermann, A. Vesseg: an open-source tool for deep learning-based atherosclerotic plaque quantification in histopathology images\u2014brief report. Arterioscler. Thromb. Vasc. Biol. 41, 2516\u20132522 (2021).","DOI":"10.1161\/ATVBAHA.121.316124"},{"key":"2829_CR22","doi-asserted-by":"crossref","unstructured":"Sharma, A., Gustafsson, F., Hartman, J. & Rantalainen, M. Multi-stain modelling of histopathology slides for breast cancer prognosis prediction. ResearchGate https:\/\/www.researchgate.net\/publication\/385927475_Multi-stain_modelling_of_histopathology_slides_for_breast_cancer_prognosis_prediction#:~:text=surgical%20resected%20specimens%20from%20945,validation%20we (2024).","DOI":"10.1101\/2024.11.10.24317066"},{"key":"2829_CR23","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1038\/s43856-025-01045-9","volume":"5","author":"Y Cheng","year":"2025","unstructured":"Cheng, Y. et al. Synergistic H&E and IHC image analysis by AI predicts cancer biomarkers and survival outcomes in colorectal and breast cancer. Commun. Med. 5, 328 (2025).","journal-title":"Commun. Med."},{"key":"2829_CR24","doi-asserted-by":"crossref","unstructured":"Abnar, S. & Zuidema, W. Quantifying attention flow in transformers. https:\/\/arxiv.org\/abs\/2005.00928 (2020).","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"2829_CR25","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1038\/nbt.4091","volume":"36","author":"L Haghverdi","year":"2018","unstructured":"Haghverdi, L., Lun, A. T. L., Morgan, M. D. & Marioni, J. C. Batch effects in single-cell RNA-sequencing data are corrected by matching mutual nearest neighbors. Nat. Biotechnol. 36, 421\u2013427 (2018).","journal-title":"Nat. Biotechnol."},{"key":"2829_CR26","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-019-1663-x","volume":"20","author":"FA Wolf","year":"2019","unstructured":"Wolf, F. A. et al. PAGA: graph abstraction reconciles clustering with trajectory inference through a topology preserving map of single cells. Genome Biol. 20, 59 (2019).","journal-title":"Genome Biol."},{"key":"2829_CR27","doi-asserted-by":"publisher","first-page":"1241","DOI":"10.1093\/bioinformatics\/btv715","volume":"32","author":"P Angerer","year":"2016","unstructured":"Angerer, P. et al. Destiny: diffusion maps for large-scale single-cell data in R. Bioinformatics 32, 1241\u20131243 (2016).","journal-title":"Bioinformatics"},{"key":"2829_CR28","doi-asserted-by":"publisher","DOI":"10.1038\/s41698-023-00352-5","volume":"7","author":"Z Huang","year":"2023","unstructured":"Huang, Z. et al. Artificial intelligence reveals features associated with breast cancer neoadjuvant chemotherapy responses from multi-stain histopathologic images. NPJ Precis. Oncol. 7, 14 (2023).","journal-title":"NPJ Precis. Oncol."},{"key":"2829_CR29","doi-asserted-by":"publisher","first-page":"102559","DOI":"10.1016\/j.media.2022.102559","volume":"81","author":"X Wang","year":"2022","unstructured":"Wang, X. et al. Transformer-based unsupervised contrastive learning for histopathological image classification. Med. Image Anal. 81, 102559 (2022).","journal-title":"Med. Image Anal."},{"key":"2829_CR30","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1109\/TPAMI.1986.4767851","volume":"8","author":"J Canny","year":"1986","unstructured":"Canny, J. A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell. 8, 679\u2013698 (1986).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2829_CR31","unstructured":"Loshchilov, I. & Hutter, F. Decoupled weight decay regularization. https:\/\/arxiv.org\/abs\/1711.05101 (2017)."},{"key":"2829_CR32","unstructured":"Jaegle, A. et al. Perceiver: General perception with iterative attention. in Proceedings of the 38th International Conference on Machine Learning (eds. Meila, M. & Zhang, T.), Vol. 139 4651\u20134664 (PMLR, 18\u201324 Jul, 2021)."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02829-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02829-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02829-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T10:57:52Z","timestamp":1782125872000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02829-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,18]]},"references-count":32,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2829"],"URL":"https:\/\/doi.org\/10.1038\/s41746-026-02829-6","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,18]]},"assertion":[{"value":"20 May 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"480"}}