{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T09:28:09Z","timestamp":1776850089993,"version":"3.51.2"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032051813","type":"print"},{"value":"9783032051820","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T00:00:00Z","timestamp":1758153600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T00:00:00Z","timestamp":1758153600000},"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\/978-3-032-05182-0_49","type":"book-chapter","created":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T00:00:22Z","timestamp":1758153622000},"page":"502-512","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PTCMIL: Multiple Instance Learning via\u00a0Prompt Token Clustering for\u00a0Whole Slide Image Analysis"],"prefix":"10.1007","author":[{"given":"Beidi","family":"Zhao","sequence":"first","affiliation":[]},{"given":"SangMook","family":"Kim","sequence":"additional","affiliation":[]},{"given":"Hao","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Chen","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Zu-hua","family":"Gao","sequence":"additional","affiliation":[]},{"given":"Gang","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Xiaoxiao","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,18]]},"reference":[{"issue":"22","key":"49_CR1","doi-asserted-by":"publisher","first-page":"2199","DOI":"10.1001\/jama.2017.14585","volume":"318","author":"BE Bejnordi","year":"2017","unstructured":"Bejnordi, B.E., et al.: Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. JAMA 318(22), 2199\u20132210 (2017)","journal-title":"JAMA"},{"issue":"1","key":"49_CR2","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1038\/s41591-021-01620-2","volume":"28","author":"W Bulten","year":"2022","unstructured":"Bulten, W., et al.: Artificial intelligence for diagnosis and Gleason grading of prostate cancer: the panda challenge. Nat. Med. 28(1), 154\u2013163 (2022)","journal-title":"Nat. Med."},{"key":"49_CR3","doi-asserted-by":"crossref","unstructured":"Cancer Genome Atlas Research\u00a0Network, J., et\u00a0al.: The cancer genome atlas pan-cancer analysis project. Nat. Genet 45(10), 1113\u20131120 (2013)","DOI":"10.1038\/ng.2764"},{"key":"49_CR4","doi-asserted-by":"crossref","unstructured":"Chan, T.H., Cendra, F.J., Ma, L., Yin, G., Yu, L.: Histopathology whole slide image analysis with heterogeneous graph representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15661\u201315670 (2023)","DOI":"10.1109\/CVPR52729.2023.01503"},{"key":"49_CR5","doi-asserted-by":"crossref","unstructured":"Chen, R.J., et al.: Scaling vision transformers to gigapixel images via hierarchical self-supervised learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16144\u201316155 (2022)","DOI":"10.1109\/CVPR52688.2022.01567"},{"issue":"3","key":"49_CR6","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1038\/s41591-024-02857-3","volume":"30","author":"RJ Chen","year":"2024","unstructured":"Chen, R.J., et al.: Towards a general-purpose foundation model for computational pathology. Nat. Med. 30(3), 850\u2013862 (2024)","journal-title":"Nat. Med."},{"key":"49_CR7","doi-asserted-by":"crossref","unstructured":"Chen, R.J., et al.: Multimodal co-attention transformer for survival prediction in gigapixel whole slide images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 4015\u20134025 (2021)","DOI":"10.1109\/ICCV48922.2021.00398"},{"key":"49_CR8","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pp. 249\u2013256. JMLR Workshop and Conference Proceedings (2010)"},{"key":"49_CR9","doi-asserted-by":"crossref","unstructured":"Hou, W., et al.: $$\\text{H}^{2}$$-mil: exploring hierarchical representation with heterogeneous multiple instance learning for whole slide image analysis. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 933\u2013941 (2022)","DOI":"10.1609\/aaai.v36i1.19976"},{"key":"49_CR10","unstructured":"Ilse, M., Tomczak, J., Welling, M.: Attention-based deep multiple instance learning. In: International Conference on Machine Learning, pp. 2127\u20132136. PMLR (2018)"},{"key":"49_CR11","unstructured":"Jain, A.K., Dubes, R.C.: Algorithms for Clustering Data. Prentice-Hall, Inc. (1988)"},{"key":"49_CR12","doi-asserted-by":"crossref","unstructured":"Jia, M., et al.: Visual prompt tuning. In: European Conference on Computer Vision, pp. 709\u2013727. Springer (2022)","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"49_CR13","doi-asserted-by":"crossref","unstructured":"Li, B., Li, Y., Eliceiri, K.W.: Dual-stream multiple instance learning network for whole slide image classification with self-supervised contrastive learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14318\u201314328 (2021)","DOI":"10.1109\/CVPR46437.2021.01409"},{"issue":"6","key":"49_CR14","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1038\/s41551-020-00682-w","volume":"5","author":"MY Lu","year":"2021","unstructured":"Lu, M.Y., Williamson, D.F., Chen, T.Y., Chen, R.J., Barbieri, M., Mahmood, F.: Data-efficient and weakly supervised computational pathology on whole-slide images. Nat. Biomed. Eng. 5(6), 555\u2013570 (2021)","journal-title":"Nat. Biomed. Eng."},{"key":"49_CR15","doi-asserted-by":"crossref","unstructured":"Marin, D., Chang, J.H.R., Ranjan, A., Prabhu, A., Rastegari, M., Tuzel, O.: Token pooling in vision transformers for image classification. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 12\u201321 (2023)","DOI":"10.1109\/WACV56688.2023.00010"},{"key":"49_CR16","first-page":"13937","volume":"34","author":"Y Rao","year":"2021","unstructured":"Rao, Y., Zhao, W., Liu, B., Lu, J., Zhou, J., Hsieh, C.J.: DynamicViT: efficient vision transformers with dynamic token sparsification. Adv. Neural. Inf. Process. Syst. 34, 13937\u201313949 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"49_CR17","first-page":"2136","volume":"34","author":"Z Shao","year":"2021","unstructured":"Shao, Z., et al.: TransMIL: transformer based correlated multiple instance learning for whole slide image classification. Adv. Neural. Inf. Process. Syst. 34, 2136\u20132147 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"49_CR18","doi-asserted-by":"crossref","unstructured":"Song, A.H., Chen, R.J., Ding, T., Williamson, D.F., Jaume, G., Mahmood, F.: Morphological prototyping for unsupervised slide representation learning in computational pathology. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11566\u201311578 (2024)","DOI":"10.1109\/CVPR52733.2024.01099"},{"key":"49_CR19","doi-asserted-by":"crossref","unstructured":"Song, A.H., Chen, R.J., Ding, T., Williamson, D.F., Jaume, G., Mahmood, F.: Morphological prototyping for unsupervised slide representation learning in computational pathology. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11566\u201311578 (2024)","DOI":"10.1109\/CVPR52733.2024.01099"},{"key":"49_CR20","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Iteratively coupled multiple instance learning from instance to bag classifier for whole slide image classification. arXiv preprint arXiv:2303.15749 (2023)","DOI":"10.1007\/978-3-031-43987-2_45"},{"key":"49_CR21","doi-asserted-by":"crossref","unstructured":"Wang, J., et\u00a0al.: Review of large vision models and visual prompt engineering. Meta-Radiol. 100047 (2023)","DOI":"10.1016\/j.metrad.2023.100047"},{"key":"49_CR22","doi-asserted-by":"publisher","first-page":"102559","DOI":"10.1016\/j.media.2022.102559","volume":"81","author":"X Wang","year":"2022","unstructured":"Wang, X., et al.: Transformer-based unsupervised contrastive learning for histopathological image classification. Med. Image Anal. 81, 102559 (2022)","journal-title":"Med. Image Anal."},{"key":"49_CR23","unstructured":"Xiang, J., Zhang, J.: Exploring low-rank property in multiple instance learning for whole slide image classification. In: The Eleventh International Conference on Learning Representations (2023)"},{"key":"49_CR24","doi-asserted-by":"publisher","first-page":"102053","DOI":"10.1016\/j.compmedimag.2022.102053","volume":"97","author":"J Yan","year":"2022","unstructured":"Yan, J., Chen, H., Li, X., Yao, J.: Deep contrastive learning based tissue clustering for annotation-free histopathology image analysis. Comput. Med. Imaging Graph. 97, 102053 (2022)","journal-title":"Comput. Med. Imaging Graph."},{"key":"49_CR25","doi-asserted-by":"crossref","unstructured":"Yang, S., Wang, Y., Chen, H.: MambaMIL: enhancing long sequence modeling with sequence reordering in computational pathology. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 296\u2013306. Springer (2024)","DOI":"10.1007\/978-3-031-72083-3_28"},{"key":"49_CR26","doi-asserted-by":"crossref","unstructured":"Zeng, W., et al.: Not all tokens are equal: Human-centric visual analysis via token clustering transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11101\u201311111 (2022)","DOI":"10.1109\/CVPR52688.2022.01082"},{"key":"49_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: DTFD-MIL: double-tier feature distillation multiple instance learning for histopathology whole slide image classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18802\u201318812 (2022)","DOI":"10.1109\/CVPR52688.2022.01824"},{"key":"49_CR28","doi-asserted-by":"crossref","unstructured":"Zhu, W., Chen, X., Qiu, P., Sotiras, A., Razi, A., Wang, Y.: DGR-MIL: exploring diverse global representation in multiple instance learning for whole slide image classification. In: European Conference on Computer Vision, pp. 333\u2013351. Springer (2024)","DOI":"10.1007\/978-3-031-72920-1_19"}],"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\/978-3-032-05182-0_49","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T08:29:00Z","timestamp":1776846540000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-05182-0_49"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,18]]},"ISBN":["9783032051813","9783032051820"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-05182-0_49","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,18]]},"assertion":[{"value":"18 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":"23 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"}}]}}