{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,22]],"date-time":"2026-02-22T07:00:35Z","timestamp":1771743635978,"version":"3.50.1"},"publisher-location":"Cham","reference-count":31,"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_23","type":"book-chapter","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T17:11:04Z","timestamp":1758301864000},"page":"240-250","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["HiLa: Hierarchical Vision-Language Collaboration for Cancer Survival Prediction"],"prefix":"10.1007","author":[{"given":"Jiaqi","family":"Cui","sequence":"first","affiliation":[]},{"given":"Lu","family":"Wen","sequence":"additional","affiliation":[]},{"given":"Yuchen","family":"Fei","sequence":"additional","affiliation":[]},{"given":"Bo","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Luping","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Dinggang","family":"Shen","sequence":"additional","affiliation":[]},{"given":"Yan","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,20]]},"reference":[{"issue":"12","key":"23_CR1","doi-asserted-by":"publisher","first-page":"930","DOI":"10.1038\/s44222-023-00096-8","volume":"1","author":"AH Song","year":"2023","unstructured":"Song, A.H., Jaume, G., Williamson, D.F., et al.: Artificial intelligence for digital and computational pathology. Nat. Rev. Bioeng. 1(12), 930\u2013949 (2023)","journal-title":"Nat. Rev. Bioeng."},{"issue":"3","key":"23_CR2","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., Ding, T., Lu, M.Y., et al.: Towards a general-purpose foundation model for computational pathology. Nat. Med. 30(3), 850\u2013862 (2024)","journal-title":"Nat. Med."},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Cui, J., Xu, Y., Zheng, H., et al.: HMT: a hybrid multi-modal transformer with multi-task learning for survival prediction in head and neck cancer. IEEE Trans. Radiat. Plasma Med. Sci. (2025)","DOI":"10.1109\/TRPMS.2025.3539739"},{"key":"23_CR4","doi-asserted-by":"publisher","first-page":"2455","DOI":"10.1109\/LSP.2024.3453196","volume":"31","author":"J Cui","year":"2024","unstructured":"Cui, J., Zheng, H., Liu, Y., et al.: Ma2SP: missing-aware prompting with modality-adaptive integration for incomplete multi-modal survival prediction. IEEE Signal Process. Lett. 31, 2455\u20132459 (2024)","journal-title":"IEEE Signal Process. Lett."},{"issue":"9","key":"23_CR5","doi-asserted-by":"publisher","first-page":"2307","DOI":"10.1038\/s41591-023-02504-3","volume":"29","author":"Z Huang","year":"2023","unstructured":"Huang, Z., Bianchi, F., Yuksekgonul, M., Montine, T.J., Zou, J.: A visual\u2013language foundation model for pathology image analysis using medical twitter. Nat. Med. 29(9), 2307\u20132316 (2023)","journal-title":"Nat. Med."},{"key":"23_CR6","first-page":"339","volume-title":"MICCAI 2021","author":"RJ Chen","year":"2021","unstructured":"Chen, R.J., Lu, M.Y., Shaban, M., et al.: Whole slide images are 2d point clouds: context-aware survival prediction using patch-based graph convolutional networks. In: de Bruijne, M., et al. (eds.) MICCAI 2021, vol. 12908, pp. 339\u2013349. Springer, Cham (2021)"},{"key":"23_CR7","doi-asserted-by":"crossref","unstructured":"Tang, W., Zhou, F., Huang, S., Zhu, X., Zhang, Y., Liu, B.: Feature re-embedding: towards foundation model-level performance in computational pathology. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11343\u201311352 (2024)","DOI":"10.1109\/CVPR52733.2024.01078"},{"key":"23_CR8","unstructured":"Ilse, M., Tomczak, J. and Welling, M.: Attention-based deep multiple instance learning. In: International Conference on Machine Learning, pp. 2127\u20132136 (2018)"},{"key":"23_CR9","unstructured":"Shao, Z., Bian, H., Chen, Y., Wang, Y., Zhang, J., Ji, X.: Transmil: transformer based correlated multiple instance learning for whole slide image classification. In: Advances in Neural Information Processing Systems, vol. 34, pp. 2136\u20132147 (2021)"},{"issue":"6","key":"23_CR10","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":"23_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.103020","volume":"91","author":"P Liu","year":"2024","unstructured":"Liu, P., Ji, L., Ye, F., Fu, B.: Advmil: adversarial multiple instance learning for the survival analysis on whole-slide images. Med. Image Anal. 91, 103020 (2024)","journal-title":"Med. Image Anal."},{"key":"23_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.106883","volume":"158","author":"S Jiang","year":"2023","unstructured":"Jiang, S., Suriawinata, A.A., Hassanpour, S.: MHAttnSurv: multi-head attention for survival prediction using whole-slide pathology images. Comput. Biol. Med. 158, 106883 (2023)","journal-title":"Comput. Biol. Med."},{"key":"23_CR13","unstructured":"Xiang, J., Zhang, J.: Exploring low-rank property in multiple instance learning for whole slide image classification. In: International Conference on Learning Representations (2023)"},{"key":"23_CR14","first-page":"713","volume-title":"MICCAI 2024","author":"J Yu","year":"2024","unstructured":"Yu, J., Wang, X., Ma, T., Li, X., Xu, Y.: Patch-slide discriminative joint learning for weakly-supervised whole slide image representation and classification. In: Linguraru, M.G., et al. (eds.) MICCAI 2024, vol. 15003, pp. 713\u2013722. Springer, Cham (2024)"},{"issue":"1","key":"23_CR15","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1109\/TMI.2023.3291719","volume":"43","author":"Z Li","year":"2023","unstructured":"Li, Z., Li, Y., Li, Q., et al.: Lvit: language meets vision transformer in medical image segmentation. IEEE Trans. Med. Imaging 43(1), 96\u2013107 (2023)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"23_CR16","first-page":"467","volume-title":"MICCAI 2024","author":"J Cui","year":"2024","unstructured":"Cui, J., Zeng, X., Zeng, P., et al.: MCAD: multi-modal conditioned adversarial diffusion model for high-quality PET image reconstruction. In: Linguraru, M.G., et al. (eds.) MICCAI 2024, vol. 15009, pp. 467\u2013477. Springer, Cham (2024)"},{"key":"23_CR17","first-page":"692","volume-title":"MICCAI 2024","author":"L Li","year":"2024","unstructured":"Li, L., Lian, S., Luo, Z., Wang, B., Li, S.: VCLIPSeg: voxel-wise CLIP-enhanced model for semi-supervised medical image segmentation. In: Linguraru, M.G., et al. (eds.) MICCAI 2024, vol. 15009, pp. 692\u2013701. Springer, Cham (2024)"},{"key":"23_CR18","first-page":"458","volume-title":"MICCAI 2024","author":"X Zhang","year":"2024","unstructured":"Zhang, X., Xu, M., Qiu, D., Yan, R., Lang, N., Zhou, X.: Mediclip: adapting clip for few-shot medical image anomaly detection. In: Linguraru, M.G., et al. (eds.) MICCAI 2024, vol. 15001, pp. 458\u2013468. Springer, Cham (2024)"},{"key":"23_CR19","first-page":"285","volume-title":"MICCAI 2024","author":"P Chikontwe","year":"2024","unstructured":"Chikontwe, P., Kang, M., Luna, M., Nam, S., Park, S.H.: Low-shot prompt tuning for multiple instance learning based histology classification. In: Linguraru, M.G., et al. (eds.) MICCAI 2024, vol. 15004, pp. 285\u2013295. Springer, Cham (2024)"},{"issue":"12","key":"23_CR20","doi-asserted-by":"publisher","first-page":"4224","DOI":"10.1109\/TMI.2024.3418408","volume":"43","author":"P Wang","year":"2024","unstructured":"Wang, P., Zhang, H., Yuan, Y.: MCPL: multi-modal collaborative prompt learning for medical vision-language model. IEEE Trans. Med. Imaging 43(12), 4224\u20134235 (2024)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"23_CR21","first-page":"272","volume-title":"MICCAI 2023","author":"Y Zhang","year":"2023","unstructured":"Zhang, Y., Gao, J., Zhou, M., et al.: Text-guided foundation model adaptation for pathological image classification. In: Greenspan, H., et al. (eds.) MICCAI 2023, vol. 13224, pp. 272\u2013282. Springer, Cham (2023)"},{"key":"23_CR22","unstructured":"Qu, L., Fu, K., Wang, M., Song, Z.: The rise of ai language pathologists: Exploring two-level prompt learning for few-shot weakly-supervised whole slide image classification. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"23_CR23","unstructured":"Liu, P., Ji, L., Gou, J., Fu, B., Ye, M.: Interpretable vision-language survival analysis with ordinal inductive bias for computational pathology. arXiv preprint arXiv:2409.09369 (2024)"},{"key":"23_CR24","first-page":"196","volume-title":"ECCV 2024","author":"L Qu","year":"2024","unstructured":"Qu, L., Yang, D., Huang, D., et al.: Pathology-knowledge enhanced multi-instance prompt learning for few-shot whole slide image classification. In: Leonardis, A., et al. (eds.) ECCV 2024, vol. 15069, pp. 196\u2013212. Springer, Cham (2024)"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Chen, R.J., Chen, C., Li, Y., 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"},{"key":"23_CR26","unstructured":"Song, A.H., Chen, R.J., Jaume, G., Vaidya, A.J., Baras, A., Mahmood, F.: Multimodal prototyping for cancer survival prediction. In: Forty-first International Conference on Machine Learning (2024)"},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Xu, Y., Chen, H.: Multimodal optimal transport-based co-attention transformer with global structure consistency for survival prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 21241\u201321251 (2023)","DOI":"10.1109\/ICCV51070.2023.01942"},{"issue":"9","key":"23_CR28","doi-asserted-by":"publisher","first-page":"3126","DOI":"10.1109\/TPAMI.2020.2979450","volume":"43","author":"SG Zadeh","year":"2020","unstructured":"Zadeh, S.G., Schmid, M.: Bias in cross-entropy-based training of deep survival networks. IEEE Trans. Pattern Anal. Mach. Intell. 43(9), 3126\u20133137 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"23_CR29","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"},{"key":"23_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, H., Meng, Y., Zhao, Y., 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":"23_CR31","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Conditional prompt learning for vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16816\u201316825 (2022)","DOI":"10.1109\/CVPR52688.2022.01631"}],"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_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,22]],"date-time":"2026-02-22T06:44:34Z","timestamp":1771742674000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04971-1_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,20]]},"ISBN":["9783032049704","9783032049711"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04971-1_23","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":"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"}}]}}