{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T07:29:04Z","timestamp":1769498944965,"version":"3.49.0"},"reference-count":36,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T00:00:00Z","timestamp":1768435200000},"content-version":"vor","delay-in-days":14,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["Int J Imaging Syst Tech"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>The Mamba model performs excellently in natural image processing but faces limitations in analyzing whole slide images (WSIs) for cancer prediction and subtype classification in digital pathology\u2014pathological images feature highly irregular lesion spatial distributions (especially complex small\u2010lesion associations), while Mamba's inherent unidirectional\/limited\u2010direction scanning cannot effectively model such multi\u2010dimensional spatial dependencies, failing to capture key pathological structural features. To address this, we propose HCSMIL, a Mamba\u2010based optimized framework tailored to pathological image clinical analysis. It comprehensively captures local lesion spatial topology via multi\u2010directional contextual modeling and integrates a multi\u2010scale pyramid structure to extract global lesion distribution features, jointly enhancing diagnostic accuracy. Validation on authoritative datasets (Camelyon16, TCGA\u2010LUNG, TCGA\u2010Kidney) shows HCSMIL significantly outperforms existing mainstream methods: on TCGA\u2010LUNG, accuracy (ACC), F1 score, and AUC are 0.66%, 1.42%, and 1.25% higher than the second\u2010best method; on TCGA\u2010Kidney, these metrics increase by 1.47%, 0.09%, and 1.00%; on Camelyon16, ACC is 0.77% higher. Notably, HCSMIL achieves an 84% small\u2010lesion recognition rate, substantially exceeding TransMIL (70.59%) and MambaMIL (64.71%), fully demonstrating its strength in capturing complexly distributed lesions and providing reliable technical support for cancer diagnosis.<\/jats:p>","DOI":"10.1002\/ima.70287","type":"journal-article","created":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T14:52:42Z","timestamp":1768488762000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi\u2010Directional Context Modeling With\n                    <scp>HCSMIL<\/scp>\n                    : Enhancing Cancer Prediction and Subtype Classification From Whole Slide Images"],"prefix":"10.1002","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2019-6903","authenticated-orcid":false,"given":"Jingtao","family":"Qiu","sequence":"first","affiliation":[{"name":"Entrepreneurship Institute Ningbo Polytechnic University  Ningbo China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4894-9284","authenticated-orcid":false,"given":"Yucheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Ningbo Alatu Digital Technology Co., Ltd  Ningbo China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2026,1,15]]},"reference":[{"key":"e_1_2_13_2_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591\u2010019\u20100508\u20101"},{"key":"e_1_2_13_3_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41551\u2010020\u201000682\u2010w"},{"key":"e_1_2_13_4_1","first-page":"529","volume-title":"Medical Image Computing and Computer\u2010Assisted Interventions (MICCAI 2020)","author":"Raju A.","year":"2020"},{"key":"e_1_2_13_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101835"},{"key":"e_1_2_13_6_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591\u2010021\u201001620\u20102"},{"key":"e_1_2_13_7_1","doi-asserted-by":"publisher","DOI":"10.1038\/s43018\u2010020\u20100085\u20108"},{"key":"e_1_2_13_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.3021387"},{"key":"e_1_2_13_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ccell.2022.07.004"},{"key":"e_1_2_13_10_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591\u2010018\u20100177\u20105"},{"key":"e_1_2_13_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1470\u20102045(20)30535\u20100"},{"key":"e_1_2_13_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102824"},{"key":"e_1_2_13_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101563"},{"key":"e_1_2_13_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2017.06.001"},{"key":"e_1_2_13_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102270"},{"key":"e_1_2_13_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2014.01.010"},{"key":"e_1_2_13_17_1","first-page":"570","article-title":"A Framework for Multiple\u2010Instance Learning","volume":"11","author":"Maron O.","year":"1998","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_13_18_1","first-page":"121","volume-title":"ICML Workshop on Learning From Multi\u2010Represented Data","author":"Ramon J.","year":"2002"},{"key":"e_1_2_13_19_1","first-page":"101","article-title":"Support Vector Machines for Multiple\u2010Instance Learning","volume":"16","author":"Andrews S.","year":"2003","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_13_20_1","first-page":"2132","volume-title":"International Conference on Machine Learning","author":"Ilse M.","year":"2018"},{"key":"e_1_2_13_21_1","first-page":"16204","volume-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Li B.","year":"2021"},{"key":"e_1_2_13_22_1","first-page":"2136","volume-title":"Advances in Neural Information Processing Systems 34 (NeurIPS 2021)","author":"Shao Z.","year":"2021"},{"key":"e_1_2_13_23_1","first-page":"206","volume-title":"Medical Image Computing and Computer\u2010Assisted Interventions (MICCAI 2021)","author":"Li H.","year":"2021"},{"key":"e_1_2_13_24_1","first-page":"420","volume-title":"Medical Image Analysis and Computer\u2010Assisted Intervention (MICCAI 2022)","author":"Chikontwe P.","year":"2022"},{"key":"e_1_2_13_25_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.03762"},{"key":"e_1_2_13_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"e_1_2_13_27_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2111.00396v3"},{"key":"e_1_2_13_28_1","unstructured":"A.GuandT.Dao \u201cMamba: Linear\u2010Time Sequence Modeling With Selective State Spaces \u201d Presented at the First Conference on Language Modeling (FCoLM) (2024) OpenReview https:\/\/doi.org\/10.48550\/arXiv.2312.00752v2."},{"key":"e_1_2_13_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM62325.2024.10822552"},{"key":"e_1_2_13_30_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2403.06800"},{"key":"e_1_2_13_31_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2401.10166"},{"key":"e_1_2_13_32_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010025\u201060307\u20101"},{"key":"e_1_2_13_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2024.3386197"},{"key":"e_1_2_13_34_1","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbae102"},{"key":"e_1_2_13_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2024.3399740"},{"key":"e_1_2_13_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_13_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263\u2010015\u20100816\u2010y"}],"container-title":["International Journal of Imaging Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/ima.70287","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/ima.70287","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/ima.70287","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T21:09:52Z","timestamp":1769461792000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/ima.70287"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1002\/ima.70287"],"URL":"https:\/\/doi.org\/10.1002\/ima.70287","archive":["Portico"],"relation":{},"ISSN":["0899-9457","1098-1098"],"issn-type":[{"value":"0899-9457","type":"print"},{"value":"1098-1098","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"2025-08-22","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-04","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70287"}}