{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T21:07:08Z","timestamp":1777496828338,"version":"3.51.4"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032049704","type":"print"},{"value":"9783032049711","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T00:00:00Z","timestamp":1758326400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T00:00:00Z","timestamp":1758326400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-04971-1_64","type":"book-chapter","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T17:10:53Z","timestamp":1758301853000},"page":"680-690","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A cartoon robot holding a digital screen displaying abstract purple patterns and a triangular shape. The robot has a friendly appearance with glowing blue eyes and metallic features. The image combines elements of technology and art, emphasizing a futuristic theme. WSI-Agents: A Collaborative Multi-agent System for\u00a0Multi-modal Whole Slide Image Analysis"],"prefix":"10.1007","author":[{"given":"Xinheng","family":"Lyu","sequence":"first","affiliation":[]},{"given":"Yuci","family":"Liang","sequence":"additional","affiliation":[]},{"given":"Wenting","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Meidan","family":"Ding","sequence":"additional","affiliation":[]},{"given":"Jiaqi","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Guolin","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Daokun","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Xiangjian","family":"He","sequence":"additional","affiliation":[]},{"given":"Linlin","family":"Shen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,20]]},"reference":[{"key":"64_CR1","unstructured":"Bosman, F.T., Carneiro, F., Hruban, R.H., Theise, N.D.: WHO classification of tumours of the digestive system. No. Ed. 4 (2010)"},{"issue":"2","key":"64_CR2","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(2), 233\u2013241 (2020)","journal-title":"Lancet Oncol."},{"key":"64_CR3","doi-asserted-by":"crossref","unstructured":"\u00c7ay\u0131r, S., et\u00a0al.: Patch-based approaches to whole slide histologic grading of breast cancer using convolutional neural networks. In: Diagnostic Biomedical Signal and Image Processing Applications with Deep Learning Methods, pp. 103\u2013118. Elsevier (2023)","DOI":"10.1016\/B978-0-323-96129-5.00007-X"},{"key":"64_CR4","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"546","DOI":"10.1007\/978-3-031-72083-3_51","volume-title":"MICCAI 2024","author":"P Chen","year":"2024","unstructured":"Chen, P., Li, H., Zhu, C., Zheng, S., Shui, Z., Yang, L.: WsiCaption: multiple instance generation of pathology reports for gigapixel whole-slide images. In: Linguraru, M.G., et al. (eds.) MICCAI 2024. LNCS, vol. 15004, pp. 546\u2013556. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72083-3_51"},{"key":"64_CR5","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1007\/978-3-031-72764-1_23","volume-title":"ECCV 2024","author":"P Chen","year":"2024","unstructured":"Chen, P., Zhu, C., Zheng, S., Li, H., Yang, L.: WSI-VQA: interpreting whole slide images by generative visual question answering. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) ECCV 2024. LNCS, vol. 15094, pp. 401\u2013417. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72764-1_23"},{"key":"64_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y., et\u00a0al.: Slidechat: a large vision-language assistant for whole-slide pathology image understanding. arXiv preprint arXiv:2410.11761 (2024)","DOI":"10.1109\/CVPR52734.2025.00484"},{"issue":"1","key":"64_CR7","doi-asserted-by":"publisher","first-page":"8894","DOI":"10.1038\/s41598-021-88494-z","volume":"11","author":"O Ciga","year":"2021","unstructured":"Ciga, O., Xu, T., Nofech-Mozes, S., Noy, S., Lu, F.I., Martel, A.L.: Overcoming the limitations of patch-based learning to detect cancer in whole slide images. Sci. Rep. 11(1), 8894 (2021)","journal-title":"Sci. Rep."},{"key":"64_CR8","unstructured":"Ding, T., et\u00a0al.: Multimodal whole slide foundation model for pathology. arXiv preprint arXiv:2411.19666 (2024)"},{"key":"64_CR9","unstructured":"Fallahpour, A., Ma, J., Munim, A., Lyu, H., Wang, B.: Medrax: medical reasoning agent for chest X-RAY. arXiv preprint arXiv:2502.02673 (2025)"},{"key":"64_CR10","series-title":"LNCS","first-page":"189","volume-title":"MICCAI 2024","author":"Z Guo","year":"2024","unstructured":"Guo, Z., Ma, J., Xu, Y., Wang, Y., Wang, L., Chen, H.: HistGEN: histopathology report generation via local-global feature encoding and cross-modal context interaction. In: Linguraru, M.G., et al. (eds.) MICCAI 2024. LNCS, vol. 15004, pp. 189\u2013199. Springer, Cham (2024)"},{"key":"64_CR11","doi-asserted-by":"crossref","unstructured":"Hashimoto, N., et al.: Multi-scale domain-adversarial multiple-instance CNN for cancer subtype classification with unannotated histopathological images. In: CVPR, pp. 3852\u20133861 (2020)","DOI":"10.1109\/CVPR42600.2020.00391"},{"key":"64_CR12","doi-asserted-by":"crossref","unstructured":"Hou, L., Samaras, D., Kurc, T.M., Gao, Y., Davis, J.E., Saltz, J.H.: Patch-based convolutional neural network for whole slide tissue image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2424\u20132433 (2016)","DOI":"10.1109\/CVPR.2016.266"},{"issue":"1","key":"64_CR13","doi-asserted-by":"publisher","first-page":"11579","DOI":"10.1038\/s41598-021-90444-8","volume":"11","author":"M Khened","year":"2021","unstructured":"Khened, M., Kori, A., Rajkumar, H., Krishnamurthi, G., Srinivasan, B.: A generalized deep learning framework for whole-slide image segmentation and analysis. Sci. Rep. 11(1), 11579 (2021)","journal-title":"Sci. Rep."},{"key":"64_CR14","unstructured":"Kim, Y., et al.: MDagents: an adaptive collaboration of LLMs in medical decision making. arXiv preprint arXiv:2404.15155 (2024)"},{"key":"64_CR15","doi-asserted-by":"crossref","unstructured":"Li, B., et\u00a0al.: MMEDagent: learning to use medical tools with multi-modal agent. arXiv preprint arXiv:2407.02483 (2024)","DOI":"10.18653\/v1\/2024.findings-emnlp.510"},{"key":"64_CR16","doi-asserted-by":"crossref","unstructured":"Liang, T., et al.: Encouraging divergent thinking in large language models through multi-agent debate. arXiv preprint arXiv:2305.19118 (2023)","DOI":"10.18653\/v1\/2024.emnlp-main.992"},{"key":"64_CR17","unstructured":"Liang, Y., et\u00a0al.: WSI-LLAVA: a multimodal large language model for whole slide image. arXiv preprint arXiv:2412.02141 (2024)"},{"key":"64_CR18","unstructured":"Liu, J., et\u00a0al.: MedChain: bridging the gap between LLM agents and clinical practice through interactive sequential benchmarking. arXiv preprint arXiv:2412.01605 (2024)"},{"key":"64_CR19","unstructured":"Liu, X., et\u00a0al.: Agentbench: Evaluating llms as agents. arXiv preprint arXiv:2308.03688"},{"issue":"3","key":"64_CR20","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1038\/s41591-024-02856-4","volume":"30","author":"MY Lu","year":"2024","unstructured":"Lu, M.Y., et al.: A visual-language foundation model for computational pathology. Nat. Med. 30(3), 863\u2013874 (2024)","journal-title":"Nat. Med."},{"key":"64_CR21","doi-asserted-by":"crossref","unstructured":"Lu, M.Y., et al.: Visual language pretrained multiple instance zero-shot transfer for histopathology images. In: CVPR, pp. 19764\u201319775 (2023)","DOI":"10.1109\/CVPR52729.2023.01893"},{"key":"64_CR22","unstructured":"Microsoft: Autogen (2023). https:\/\/github.com\/microsoft\/autogen, 2025-02-27"},{"issue":"2","key":"64_CR23","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1111\/his.13975","volume":"76","author":"ID Nagtegaal","year":"2019","unstructured":"Nagtegaal, I.D., et al.: The 2019 who classification of Tumours of the digestive system. Histopathology 76(2), 182 (2019)","journal-title":"Histopathology"},{"key":"64_CR24","unstructured":"PathologyOutlines (2001). https:\/\/PathologyOutlines.com, 2025-02-27"},{"key":"64_CR25","unstructured":"Qian, C., et al.: Communicative agents for software development. arXiv preprint arXiv:2307.07924 (2023)"},{"key":"64_CR26","doi-asserted-by":"crossref","unstructured":"Seyfioglu, M.S., Ikezogwo, W.O., Ghezloo, F., Krishna, R., Shapiro, L.: Quilt-LLAVA: visual instruction tuning by extracting localized narratives from open-source histopathology videos. In: Proceedings of the IEEE\/CVF CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01252"},{"key":"64_CR27","unstructured":"Shaikovski, G., Casson, A., Severson, K., Zimmermann, E., Wang, Y.K., et\u00a0al.: Prism: a multi-modal generative foundation model for slide-level histopathology. arXiv preprint arXiv:2405.10254 (2024)"},{"key":"64_CR28","doi-asserted-by":"crossref","unstructured":"Tan, P.H., et\u00a0al.: The 2019 who classification of tumours of the breast. Histopathology 77(2) (2020)","DOI":"10.1111\/his.14091"},{"key":"64_CR29","doi-asserted-by":"crossref","unstructured":"Tang, X., et al.: Medagents: large language models as collaborators for zero-shot medical reasoning. arXiv preprint arXiv:2311.10537 (2023)","DOI":"10.18653\/v1\/2024.findings-acl.33"},{"key":"64_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2020.101838","volume":"87","author":"S Tripathi","year":"2021","unstructured":"Tripathi, S., Singh, S.K., Lee, H.K.: An end-to-end breast tumour classification model using context-based patch modelling-a bilstm approach for image classification. Comput. Med. Imaging Graph. 87, 101838 (2021)","journal-title":"Comput. Med. Imaging Graph."},{"key":"64_CR31","unstructured":"Wang, H., Zhao, S., Qiang, Z., Xi, N., Qin, B., Liu, T.: Beyond direct diagnosis: LLM-based multi-specialist agent consultation for automatic diagnosis. arXiv preprint arXiv:2401.16107 (2024)"},{"key":"64_CR32","unstructured":"Xu, H., et\u00a0al.: A whole-slide foundation model for digital pathology from real-world data. Nature 1\u20138 (2024)"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04971-1_64","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,22]],"date-time":"2026-02-22T06:45:52Z","timestamp":1771742752000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04971-1_64"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,20]]},"ISBN":["9783032049704","9783032049711"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04971-1_64","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,20]]},"assertion":[{"value":"20 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"MICCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Medical Image Computing and Computer-Assisted Intervention","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}