{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T12:13:27Z","timestamp":1790338407334,"version":"4.1.0"},"reference-count":27,"publisher":"Wiley","issue":"3","license":[{"start":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T00:00:00Z","timestamp":1766448000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T00:00:00Z","timestamp":1766448000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Cancer Science"],"published-print":{"date-parts":[[2026,3]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Accurate primary tumor (pT) staging in muscle\u2010invasive bladder cancer (MIBC) is crucial for treatment and prognosis. Current methods require time\u2010consuming, labor\u2010intensive microscopic evaluation by pathologists, with inherent interobserver variability. There is a need for AI\u2010driven automated diagnosis of whole\u2010slide images (WSI) to improve diagnostic efficiency while maintaining accuracy in pT staging. We obtained 281 H&amp;E\u2010stained WSI samples from the TCGA dataset for developing and validating a graph neural network (GNN)\u2010based diagnostic model, and 83 additional samples from a hospital for external validation. The GNN method integrated multi\u2010scale WSI data, evaluated using areas under the curve (AUC), accuracy, sensitivity, and specificity. A multi\u2010scale attention mechanism was added to enhance model interpretability by capturing pT staging infiltration patterns. Diagnostic results were compared with those of three pathologists of varying expertise. We developed the multi\u2010scale WSI\u2010integrated GNN model for histopathological staging (T2\/T3\/T4) of MIBC. The model demonstrated excellent performance on external validation, achieving an AUC of 0.911 and an accuracy of 0.905. Interpretability analysis revealed distinct infiltration patterns for each T\u2010stage, while diagnostic comparisons against both ground truth and three independent pathologists showed strong agreement, with a Cohen's kappa coefficient exceeding 0.876. The model developed based on graph neural network methods can integrate multi\u2010scale information from whole\u2010slide tissue images, allowing it to capture key infiltration patterns for muscle\u2010invasive bladder cancer pT staging. This enables precise pT staging and visualizes the multi\u2010scale tumor infiltration regions through attention scores, with accuracy showing strong consistency with expert pathologists.<\/jats:p>","DOI":"10.1111\/cas.70292","type":"journal-article","created":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T05:58:12Z","timestamp":1766555892000},"page":"864-875","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Graph Neural Network\u2010Based Multi\u2010Scale Whole Slide Image Fusion for\n                    <scp>pT<\/scp>\n                    Staging of Muscle\u2010Invasive Bladder Cancer"],"prefix":"10.1111","volume":"117","author":[{"given":"Qian","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer and Information Engineering Guangxi Vocational Normal University  Nanning China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing Feng","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer, Electronics and Information Guangxi University  Nanning China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0870-4728","authenticated-orcid":false,"given":"Nan Qing","family":"Liao","sequence":"additional","affiliation":[{"name":"Department of Plastic Surgery and Burns, Affiliated Hospital of Zunyi Medical University  Zunyi China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,12,23]]},"reference":[{"key":"e_1_2_13_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.euo.2022.04.008"},{"key":"e_1_2_13_3_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1464-410X.2005.05401.x"},{"key":"e_1_2_13_4_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12916-021-01953-2"},{"key":"e_1_2_13_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2020.3040269"},{"key":"e_1_2_13_6_1","doi-asserted-by":"publisher","DOI":"10.1002\/hep.31207"},{"key":"e_1_2_13_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1470-2045(19)30154-8"},{"key":"e_1_2_13_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2020.101846"},{"key":"e_1_2_13_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.120"},{"key":"e_1_2_13_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2529665"},{"key":"e_1_2_13_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/b117970"},{"key":"e_1_2_13_12_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-020-00682-w"},{"key":"e_1_2_13_13_1","unstructured":"Z.Shao H.Bian Y.Chen et\u00a0al. \u201cTransMIL: Transformer Based Correlated Multiple Instance Learning for Whole Slide Image Classification \u201dProceedings of the 35th International Conference on Neural Information Processing Systems Curran Associates Inc.; 2021: 164."},{"key":"e_1_2_13_14_1","unstructured":"M.Ilse J.Tomczak andM.Welling \u201cAttention\u2010Based Deep Multiple Instance Learning \u201dProceedings of the 35th International Conference on Machine Learning. Edited by Jennifer D Andreas K Proceedings of Machine Learning Research: PMLR; 2018 vol. 80: 2127\u20132136."},{"key":"e_1_2_13_15_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-41595-2"},{"key":"e_1_2_13_16_1","doi-asserted-by":"publisher","DOI":"10.3390\/cancers14235807"},{"key":"e_1_2_13_17_1","doi-asserted-by":"publisher","DOI":"10.3390\/cancers15061673"},{"key":"e_1_2_13_18_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2021.654685"},{"key":"e_1_2_13_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104932"},{"key":"e_1_2_13_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.2971006"},{"key":"e_1_2_13_21_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12885-023-11516-8"},{"key":"e_1_2_13_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2025.3581083"},{"key":"e_1_2_13_23_1","doi-asserted-by":"publisher","DOI":"10.3934\/mbe.2023496"},{"key":"e_1_2_13_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2023.107789"},{"key":"e_1_2_13_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3236162"},{"key":"e_1_2_13_26_1","doi-asserted-by":"crossref","unstructured":"S.Fuster F.Khoraminia U.Kiraz et\u00a0al. \u201cInvasive Cancerous Area Detection in Non\u2010Muscle Invasive Bladder Cancer Whole Slide Images \u201d2022 IEEE 14th Image Video and Multidimensional Signal Processing Workshop (IVMSP): 2022. IEEE: 1\u20135.","DOI":"10.1109\/IVMSP54334.2022.9816352"},{"key":"e_1_2_13_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102824"},{"key":"e_1_2_13_28_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12967-023-03888-z"}],"container-title":["Cancer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cas.70292","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/cas.70292","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cas.70292","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T10:41:31Z","timestamp":1772966491000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/cas.70292"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,23]]},"references-count":27,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["10.1111\/cas.70292"],"URL":"https:\/\/doi.org\/10.1111\/cas.70292","archive":["Portico"],"relation":{},"ISSN":["1347-9032","1349-7006"],"issn-type":[{"value":"1347-9032","type":"print"},{"value":"1349-7006","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,23]]},"assertion":[{"value":"2025-08-08","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-26","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}