{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T23:35:34Z","timestamp":1761176134801,"version":"build-2065373602"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643686318","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T00:00:00Z","timestamp":1761004800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,21]]},"abstract":"<jats:p>Multiple instance learning (MIL) has became a dominant strategy for histopathological whole slide image (WSI) analysis, enabling slide-level prediction from patch-based inputs under weak supervision. While recent transformer- and graph-based MIL methods have improved performance by modeling inter-patch relationships, they face two critical limitations: computational inefficiency when processing ultra-long sequences inherent to gigapixel WSIs, and insufficient interpretability due to the absence of robust quantitative evaluation frameworks. To address these challenges, we propose WSiG, a novel graph neural network framework integrating: (i) a gate-attention distance module that optimizes dynamic graph construction complexity and (ii) a query-aware aggregation mechanism that strengthens feature aggregation and distinction. Extensive experiments on two public datasets (CAMELYON and PANDA) demonstrate WSiG\u2019s superiority, achieving state-of-the-art AUCs of 97.9% and 99.65%, respectively, with minimal computational complexity. In addition, quantitative interpretability analysis demonstrated WSiG\u2019s precise localization of diagnostically relevant regions, further supporting its reliability in practical applications. The code will be publicly available at https:\/\/github.com\/GaryinDeep\/WSiG.<\/jats:p>","DOI":"10.3233\/faia250862","type":"book-chapter","created":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T09:44:25Z","timestamp":1761126265000},"source":"Crossref","is-referenced-by-count":0,"title":["WSiG: A Graph Neural Network for Whole Slide Image Classification"],"prefix":"10.3233","author":[{"given":"Guangjian","family":"Zeng","sequence":"first","affiliation":[{"name":"School of Public Health and Emergency Management, Southern University of Science and Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siyuan","family":"Tao","sequence":"additional","affiliation":[{"name":"School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tian","family":"Mou","sequence":"additional","affiliation":[{"name":"School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","ECAI 2025"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA250862","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T09:44:25Z","timestamp":1761126265000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA250862"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,21]]},"ISBN":["9781643686318"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia250862","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,21]]}}}