{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:12:15Z","timestamp":1764785535170,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T00:00:00Z","timestamp":1734307200000},"content-version":"vor","delay-in-days":24,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"US National Science Foundation","award":["IIS-2412195, CCF-2400785"],"award-info":[{"award-number":["IIS-2412195, CCF-2400785"]}]},{"name":"Cancer Prevention and Research Institute of Texas (CPRIT)","award":["RP230363"],"award-info":[{"award-number":["RP230363"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,11,22]]},"DOI":"10.1145\/3698587.3701372","type":"proceedings-article","created":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T10:05:08Z","timestamp":1734343508000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["MFMF: Multiple Foundation Model Fusion Networks for Whole Slide Image Classification"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7629-3853","authenticated-orcid":false,"given":"Thao M.","family":"Dang","sequence":"first","affiliation":[{"name":"University of Texas at Arlington, Arlington, Texas, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8993-1818","authenticated-orcid":false,"given":"Yuzhi","family":"Guo","sequence":"additional","affiliation":[{"name":"University of Texas at Arlington, Arlington, Texas, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5971-0053","authenticated-orcid":false,"given":"Hehuan","family":"Ma","sequence":"additional","affiliation":[{"name":"University of Texas at Arlington, Arlington, Texas, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5398-3970","authenticated-orcid":false,"given":"Qifeng","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Texas at Arlington, Arlington, Texas, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2662-5063","authenticated-orcid":false,"given":"Saiyang","family":"Na","sequence":"additional","affiliation":[{"name":"University of Texas at Arlington, Arlington, Texas, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9077-7803","authenticated-orcid":false,"given":"Jean","family":"Gao","sequence":"additional","affiliation":[{"name":"University of Texas at Arlington, Arlington, Texas, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9548-1227","authenticated-orcid":false,"given":"Junzhou","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Texas at Arlington, Arlington, Texas, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,12,16]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","unstructured":"Watson M. Holback C. Jarosz R. Kirk S. Lee Y. Rieger-Christ K. Lemmerman J. Albertina B. 2016. The Cancer Genome Atlas Lung Adenocarcinoma Collection (TCGA-LUAD). The Cancer Imaging Archive. https:\/\/doi.org\/10.7937\/K9\/TCIA.2016.JGNIHEP5","DOI":"10.7937\/K9\/TCIA.2016.JGNIHEP5"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01567"},{"key":"e_1_3_2_2_3_1","volume-title":"NeurIPS 2021","author":"Chen Richard J","year":"2021","unstructured":"Richard J Chen and Rahul G Krishnan. 2021. Self-Supervised Vision Transformers Learn Visual Concepts in Histopathology. Learning Meaningful Representations of Life, NeurIPS 2021 (2021)."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2017.14585"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41568-021-00399-1"},{"key":"e_1_3_2_2_6_1","volume-title":"34th British Machine Vision Conference 2023, BMVC 2023","author":"Holdenried-Krafft Simon","year":"2023","unstructured":"Simon Holdenried-Krafft, Peter Somers, Ivonne Montes-Mojarro, Diana Silimon, Cristina Tar\u00edn, Falko Fend, and Hendrik P. A. Lensch. 2023. Dual-Query Multiple Instance Learning for Dynamic Meta-Embedding based Tumor Classification. In 34th British Machine Vision Conference 2023, BMVC 2023, Aberdeen, UK, November 20-24, 2023. BMVA."},{"key":"e_1_3_2_2_7_1","volume-title":"International conference on machine learning. PMLR, 2127--2136","author":"Ilse Maximilian","year":"2018","unstructured":"Maximilian Ilse, Jakub Tomczak, and Max Welling. 2018. Attention-based deep multiple instance learning. In International conference on machine learning. PMLR, 2127--2136."},{"key":"e_1_3_2_2_8_1","volume-title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs. In International Conference on Learning Representations.","author":"Jaegle Andrew","year":"2022","unstructured":"Andrew Jaegle, Sebastian Borgeaud, Jean-Baptiste Alayrac, Carl Doersch, Catalin Ionescu, David Ding, Skanda Koppula, Daniel Zoran, Andrew Brock, Evan Shelhamer, Olivier J Henaff, Matthew Botvinick, Andrew Zisserman, Oriol Vinyals, and Joao Carreira. 2022. Perceiver IO: A General Architecture for Structured Inputs & Outputs. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbae343"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","unstructured":"Lee Y. Kumar P. Filippini J. Albertina B. Watson M. Rieger-Christ K. Lemmerman J. Kirk S. 2016. The Cancer Genome Atlas Lung Squamous Cell Carcinoma Collection (TCGA-LUSC). https:\/\/doi.org\/10.7937\/K9\/TCIA.2016.TYGKKFMQ","DOI":"10.7937\/K9\/TCIA.2016.TYGKKFMQ"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01409"},{"key":"e_1_3_2_2_12_1","volume-title":"Llava-med: Training a large language-and-vision assistant for biomedicine in one day. arXiv preprint arXiv:2306.00890","author":"Li Chunyuan","year":"2023","unstructured":"Chunyuan Li, Cliff Wong, Sheng Zhang, Naoto Usuyama, Haotian Liu, Jianwei Yang, Tristan Naumann, Hoifung Poon, and Jianfeng Gao. 2023. Llava-med: Training a large language-and-vision assistant for biomedicine in one day. arXiv preprint arXiv:2306.00890 (2023)."},{"key":"e_1_3_2_2_13_1","unstructured":"Haotian Liu Chunyuan Li Qingyang Wu and Yong Jae Lee. 2023. Visual Instruction Tuning."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-02856-4"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-02856-4"},{"key":"e_1_3_2_2_16_1","volume-title":"Tiffany Y Chen, Richard J Chen, Matteo Barbieri, and Faisal Mahmood.","author":"Lu Ming Y","year":"2021","unstructured":"Ming Y Lu, Drew FK Williamson, Tiffany Y Chen, Richard J Chen, Matteo Barbieri, and Faisal Mahmood. 2021. Data-efficient and weakly supervised computational pathology on whole-slide images. Nature biomedical engineering 5, 6 (2021), 555--570."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2009.5193250"},{"key":"e_1_3_2_2_18_1","volume-title":"Segment Any Cell: A SAM-based Auto-prompting Fine-tuning Framework for Nuclei Segmentation. ArXiv abs\/2401.13220","author":"Na Saiyang","year":"2024","unstructured":"Saiyang Na, Yuzhi Guo, Feng Jiang, Hehuan Ma, and Junzhou Huang. 2024. Segment Any Cell: A SAM-based Auto-prompting Fine-tuning Framework for Nuclei Segmentation. ArXiv abs\/2401.13220 (2024)."},{"key":"e_1_3_2_2_19_1","volume-title":"Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology Videos. arXiv e-prints","author":"Seyfioglu Mehmet Saygin","year":"2023","unstructured":"Mehmet Saygin Seyfioglu, Wisdom O Ikezogwo, Fatemeh Ghezloo, Ranjay Krishna, and Linda Shapiro. 2023. Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology Videos. arXiv e-prints (2023), arXiv-2312."},{"key":"e_1_3_2_2_20_1","volume-title":"Transmil: Transformer based correlated multiple instance learning for whole slide image classification. Advances in neural information processing systems 34","author":"Shao Zhuchen","year":"2021","unstructured":"Zhuchen Shao, Hao Bian, Yang Chen, Yifeng Wang, Jian Zhang, Xiangyang Ji, et al. 2021. Transmil: Transformer based correlated multiple instance learning for whole slide image classification. Advances in neural information processing systems 34 (2021), 2136--2147."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1038\/s44222-023-00096-8"},{"key":"e_1_3_2_2_22_1","volume-title":"\u0141 ukasz Kaiser, and Illia Polosukhin","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141 ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102890"},{"key":"e_1_3_2_2_24_1","volume-title":"Exploring Low-Rank Property in Multiple Instance Learning for Whole Slide Image Classification. In The Eleventh International Conference on Learning Representations.","author":"Xiang Jinxi","year":"2023","unstructured":"Jinxi Xiang and Jun Zhang. 2023. Exploring Low-Rank Property in Multiple Instance Learning for Whole Slide Image Classification. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101789"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01964"},{"key":"e_1_3_2_2_27_1","volume-title":"PathM3: A Multimodal Multi-Task Multiple Instance Learning Framework for Whole Slide Image Classification and Captioning. arXiv preprint arXiv:2403.08967","author":"Zhou Qifeng","year":"2024","unstructured":"Qifeng Zhou, Wenliang Zhong, Yuzhi Guo, Michael Xiao, Hehuan Ma, and Jun-zhou Huang.2024. PathM3: A Multimodal Multi-Task Multiple Instance Learning Framework for Whole Slide Image Classification and Captioning. arXiv preprint arXiv:2403.08967 (2024)."}],"event":{"name":"BCB '24: 15th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","sponsor":["SIGBio ACM Special Interest Group on Bioinformatics"],"location":"Shenzhen China","acronym":"BCB '24"},"container-title":["Proceedings of the 15th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3698587.3701372","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3698587.3701372","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3698587.3701372","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T11:24:40Z","timestamp":1755861880000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3698587.3701372"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"references-count":27,"alternative-id":["10.1145\/3698587.3701372","10.1145\/3698587"],"URL":"https:\/\/doi.org\/10.1145\/3698587.3701372","relation":{},"subject":[],"published":{"date-parts":[[2024,11,22]]},"assertion":[{"value":"2024-12-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}