{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T03:52:06Z","timestamp":1779335526910,"version":"3.51.4"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T00:00:00Z","timestamp":1761264000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T00:00:00Z","timestamp":1761264000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>This study proposes a deep learning approach for classifying normal, noninvasive, and invasive urothelial neoplasms via digitized histopathologicalimages. Despite many artificial intelligence (AI) models for cancer diagnosis, few focus on bladder lesions or differentiate between these critical categories. We developed convolutional neural networks (CNNs) and transformer-based models, which were trained on 12,500 whole-slide images (WSIs) from five institutions, with preprocessing steps including stain normalization and patch extraction. Fivefold cross-validation was used for evaluation against expert-annotated labels. Among tested models, EfficientNet-B6 achieved the highest performance, with an accuracy of 0.913 (95% confidence interval (CI), 0.907\u20130.920), sensitivity of 0.909 (95% CI, 0.904\u20130.914), specificity of 0.956 (95% CI, 0.953\u20130.960), F1-score of 0.906 (95% CI, 0.901\u20130.911), and an area under the receiver operating characteristic curve (AUC) of 0.983 (95% CI, 0.982\u20130.984). These results demonstrate the effectiveness and generalizability of AI-based bladder cancer classification.<\/jats:p>","DOI":"10.1038\/s41598-025-21096-1","type":"journal-article","created":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T08:37:14Z","timestamp":1761295034000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Multi-institutional validation of AI models for classifying urothelial neoplasms in digital pathology"],"prefix":"10.1038","volume":"15","author":[{"given":"Jun Young","family":"Park","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jisup","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Young Jae","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sung Hyun","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chi Sung","family":"An","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kwang Gi","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chan Kwon","family":"Jung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,24]]},"reference":[{"key":"21096_CR1","doi-asserted-by":"publisher","first-page":"394","DOI":"10.3322\/caac.21492","volume":"68","author":"F Bray","year":"2018","unstructured":"Bray, F. et al. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. Cancer J. Clin. 68, 394\u2013424 (2018).","journal-title":"Cancer J. Clin."},{"key":"21096_CR2","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1016\/j.euf.2016.04.010","volume":"2","author":"V Panebianco","year":"2016","unstructured":"Panebianco, V. et al. Improving staging in bladder cancer: the increasing role of multiparametric magnetic resonance imaging. Eur. Urol. Focus. 2, 113\u2013121 (2016).","journal-title":"Eur. Urol. Focus"},{"key":"21096_CR3","doi-asserted-by":"publisher","first-page":"04109","DOI":"10.7189\/jogh.13.04109","volume":"13","author":"Y Zhang","year":"2023","unstructured":"Zhang, Y. et al. The global landscape of bladder cancer incidence and mortality in 2020 and projections to 2040. J. Global Health. 13, 04109 (2023).","journal-title":"J. Global Health"},{"key":"21096_CR4","first-page":"507","volume":"96","author":"KC DeGeorge","year":"2017","unstructured":"DeGeorge, K. C., Holt, H. R. & Hodges, S. C. Bladder cancer: diagnosis and treatment. Am. Family Phys. 96, 507\u2013514 (2017).","journal-title":"Am. Family Phys."},{"key":"21096_CR5","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1016\/j.eururo.2016.02.028","volume":"70","author":"PA Humphrey","year":"2016","unstructured":"Humphrey, P. A., Moch, H., Cubilla, A. L., Ulbright, T. M. & Reuter, V. E. The 2016 WHO classification of tumours of the urinary system and male genital organs\u2014part B: prostate and bladder tumours. Eur. Urol. 70, 106\u2013119 (2016).","journal-title":"Eur. Urol."},{"key":"21096_CR6","doi-asserted-by":"publisher","first-page":"40","DOI":"10.4103\/jpi.jpi_69_18","volume":"9","author":"L Pantanowitz","year":"2018","unstructured":"Pantanowitz, L. et al. Twenty years of digital pathology: an overview of the road travelled, what is on the horizon, and the emergence of vendor-neutral archives. J. Pathol. Inf. 9, 40 (2018).","journal-title":"J. Pathol. Inf."},{"key":"21096_CR7","doi-asserted-by":"publisher","first-page":"2255","DOI":"10.21037\/tlcr-20-591","volume":"9","author":"T Sakamoto","year":"2020","unstructured":"Sakamoto, T. et al. A narrative review of digital pathology and artificial intelligence: focusing on lung cancer. Translational Lung Cancer Res. 9, 2255 (2020).","journal-title":"Translational Lung Cancer Res."},{"key":"21096_CR8","doi-asserted-by":"publisher","first-page":"1063","DOI":"10.1111\/his.12879","volume":"68","author":"DR Snead","year":"2016","unstructured":"Snead, D. R. et al. Validation of digital pathology imaging for primary histopathological diagnosis. Histopathology 68, 1063\u20131072 (2016).","journal-title":"Histopathology"},{"key":"21096_CR9","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1016\/S1470-2045(19)30739-9","volume":"21","author":"W Bulten","year":"2020","unstructured":"Bulten, W. et al. Automated deep-learning system for Gleason grading of prostate cancer using biopsies: a diagnostic study. Lancet Oncol. 21, 233\u2013241 (2020).","journal-title":"Lancet Oncol."},{"key":"21096_CR10","doi-asserted-by":"publisher","first-page":"963","DOI":"10.1016\/j.bbe.2022.07.006","volume":"42","author":"R Karthik","year":"2022","unstructured":"Karthik, R., Menaka, R. & Siddharth, M. Classification of breast cancer from histopathology images using an ensemble of deep multiscale networks. Biocybernetics Biomedical Eng. 42, 963\u2013976 (2022).","journal-title":"Biocybernetics Biomedical Eng."},{"key":"21096_CR11","doi-asserted-by":"publisher","first-page":"22533","DOI":"10.1038\/s41598-024-73823-9","volume":"14","author":"M Zubair","year":"2024","unstructured":"Zubair, M. et al. Enhanced gastric cancer classification and quantification interpretable framework using digital histopathology images. Sci. Rep. 14, 22533 (2024).","journal-title":"Sci. Rep."},{"key":"21096_CR12","doi-asserted-by":"publisher","first-page":"1745","DOI":"10.1038\/s41598-025-85857-8","volume":"15","author":"SW Moon","year":"2025","unstructured":"Moon, S. W. et al. Leveraging explainable AI and large-scale datasets for comprehensive classification of renal histologic types. Sci. Rep. 15, 1745 (2025).","journal-title":"Sci. Rep."},{"key":"21096_CR13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12911-019-1002-x","volume":"20","author":"PN Yin","year":"2020","unstructured":"Yin, P. N. et al. Histopathological distinction of non-invasive and invasive bladder cancers using machine learning approaches. BMC Med. Inf. Decis. Mak. 20, 1\u201311 (2020).","journal-title":"BMC Med. Inf. Decis. Mak."},{"key":"21096_CR14","doi-asserted-by":"publisher","first-page":"909","DOI":"10.3390\/bioengineering11090909","volume":"11","author":"S Fuster","year":"2024","unstructured":"Fuster, S., Kiraz, U., Eftest\u00f8l, T., Janssen, E. A. & Engan, K. NMGrad: advancing histopathological bladder cancer grading with weakly supervised deep learning. Bioengineering 11, 909 (2024).","journal-title":"Bioengineering"},{"key":"21096_CR15","doi-asserted-by":"publisher","first-page":"e307","DOI":"10.1016\/j.clgc.2016.01.002","volume":"14","author":"F Giunchi","year":"2016","unstructured":"Giunchi, F. et al. Role of inter-observer variability and quantification of muscularis propria in the pathological staging of bladder cancer. Clin. Genitourin. Cancer. 14, e307\u2013e312 (2016).","journal-title":"Clin. Genitourin. Cancer"},{"key":"21096_CR16","unstructured":"Amin, M. B. et al. AJCC Cancer Staging ManualVol. 1024 (Springer, 2017)."},{"key":"21096_CR17","unstructured":"Tan, M. & Le, Q. in International conference on machine learning. 6105\u20136114 (PMLR)."},{"key":"21096_CR18","doi-asserted-by":"publisher","first-page":"737","DOI":"10.1056\/NEJM199203123261104","volume":"326","author":"D Sidransky","year":"1992","unstructured":"Sidransky, D. et al. Clonal origin of bladder cancer. N. Engl. J. Med. 326, 737\u2013740 (1992).","journal-title":"N. Engl. J. Med."},{"key":"21096_CR19","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1038\/s41586-024-07441-w","volume":"630","author":"H Xu","year":"2024","unstructured":"Xu, H. et al. A whole-slide foundation model for digital pathology from real-world data. Nature 630, 181\u2013188 (2024).","journal-title":"Nature"},{"key":"21096_CR20","unstructured":"Kumar, N. et al. Single GPU Task Adaptation of Pathology Foundation Models for Whole Slide Image Analysis. arXiv preprint arXiv:2506.05184 (2025)."},{"key":"21096_CR21","doi-asserted-by":"publisher","first-page":"87","DOI":"10.3390\/asi5050087","volume":"5","author":"A Ashtaiwi","year":"2022","unstructured":"Ashtaiwi, A. Optimal histopathological magnification factors for deep learning-based breast cancer prediction. Appl. Syst. Innov. 5, 87 (2022).","journal-title":"Appl. Syst. Innov."},{"key":"21096_CR22","doi-asserted-by":"publisher","first-page":"1487","DOI":"10.1038\/s41379-021-00807-9","volume":"34","author":"TM D\u2019Alfonso","year":"2021","unstructured":"D\u2019Alfonso, T. M. et al. Multi-magnification-based machine learning as an ancillary tool for the pathologic assessment of shaved margins for breast carcinoma lumpectomy specimens. Mod. Pathol. 34, 1487\u20131494 (2021).","journal-title":"Mod. Pathol."},{"key":"21096_CR23","unstructured":"Paszke, A. & Pytorch An imperative style, high-performance deep learning library. arXiv preprint arXiv:.01703 (2019). (2019). (1912)."},{"key":"21096_CR24","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1016\/0169-2607(95)01703-8","volume":"48","author":"F Schoonjans","year":"1995","unstructured":"Schoonjans, F., Zalata, A., Depuydt, C. & Comhaire, F. MedCalc: a new computer program for medical statistics. Comput. Methods Programs Biomed. 48, 257\u2013262 (1995).","journal-title":"Comput. Methods Programs Biomed."},{"key":"21096_CR25","first-page":"120","volume":"25","author":"G Bradski","year":"2000","unstructured":"Bradski, G. The Opencv library. Dr Dobb\u2019s Journal: Softw. Tools Prof. Program. 25, 120\u2013123 (2000).","journal-title":"Dr Dobb\u2019s Journal: Softw. Tools Prof. Program."},{"key":"21096_CR26","first-page":"2825","volume":"12","author":"P Fabian","year":"2011","unstructured":"Fabian, P. Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12, 2825 (2011).","journal-title":"J. Mach. Learn. Res."},{"key":"21096_CR27","unstructured":"Abe, T., Yamaguchi, M., Murakami, Y., Ohyama, N. & Yagi, Y. in Proceedings. 6th International Workshop on Enterprise Networking and Computing in Healthcare Industry-Healthcom 2004 (IEEE Cat. No. 04EX842). 218\u2013223 (IEEE)."},{"key":"21096_CR28","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1016\/j.micron.2018.07.005","volume":"114","author":"S Roy","year":"2018","unstructured":"Roy, S., Jain, Lal, A., Kini, J. & S. & A study about color normalization methods for histopathology images. Micron 114, 42\u201361 (2018).","journal-title":"Micron"},{"key":"21096_CR29","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. in Proceedings of the IEEE conference on computer vision and pattern recognition. 770\u2013778."},{"key":"21096_CR30","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L. & Weinberger, K. Q. in Proceedings of the IEEE conference on computer vision and pattern recognition. 4700\u20134708."},{"key":"21096_CR31","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D. & Zhai, X. in International Conference on Learning Representations. 3."},{"key":"21096_CR32","unstructured":"Vaswani, A. et al. Attention is all you need. Advances Neural Inform. Process. Systems 30 (2017)."},{"key":"21096_CR33","unstructured":"Dosovitskiy, A. et al. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:.11929 (2020). (2020). (2010)."},{"key":"21096_CR34","doi-asserted-by":"crossref","unstructured":"McInnes, L., Healy, J., Melville, J. & Umap Uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426 (2018).","DOI":"10.21105\/joss.00861"},{"key":"21096_CR35","doi-asserted-by":"publisher","first-page":"22","DOI":"10.4097\/kjae.2017.70.1.22","volume":"70","author":"TK Kim","year":"2017","unstructured":"Kim, T. K. Understanding one-way ANOVA using conceptual figures. Korean J. Anesthesiology. 70, 22 (2017).","journal-title":"Korean J. Anesthesiology"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-21096-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-21096-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-21096-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T08:37:23Z","timestamp":1761295043000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-21096-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,24]]},"references-count":35,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["21096"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-21096-1","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,24]]},"assertion":[{"value":"16 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"37215"}}