{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T03:14:46Z","timestamp":1769829286846,"version":"3.49.0"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732461","type":"print"},{"value":"9783031732478","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-73247-8_12","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T12:02:20Z","timestamp":1730376140000},"page":"196-212","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Pathology-Knowledge Enhanced Multi-instance Prompt Learning for Few-Shot\u00a0Whole\u00a0Slide\u00a0Image\u00a0Classification"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8815-7050","authenticated-orcid":false,"given":"Linhao","family":"Qu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1829-5671","authenticated-orcid":false,"given":"Dingkang","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Dan","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Qinhao","family":"Guo","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4118-7225","authenticated-orcid":false,"given":"Rongkui","family":"Luo","sequence":"additional","affiliation":[]},{"given":"Shaoting","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3840-5658","authenticated-orcid":false,"given":"Xiaosong","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"12_CR1","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 35, pp. 23716\u201323736 (2022)"},{"issue":"8","key":"12_CR2","doi-asserted-by":"publisher","first-page":"1301","DOI":"10.1038\/s41591-019-0508-1","volume":"25","author":"G Campanella","year":"2019","unstructured":"Campanella, G., et al.: Clinical-grade computational pathology using weakly supervised deep learning on whole slide images. Nat. Med. 25(8), 1301\u20131309 (2019)","journal-title":"Nat. Med."},{"key":"12_CR3","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 (CVPR), pp. 15661\u201315670 (2023)","DOI":"10.1109\/CVPR52729.2023.01503"},{"key":"12_CR4","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 (CVPR), pp. 16144\u201316155 (2022)","DOI":"10.1109\/CVPR52688.2022.01567"},{"issue":"4","key":"12_CR5","doi-asserted-by":"publisher","first-page":"757","DOI":"10.1109\/TMI.2020.3021387","volume":"41","author":"RJ Chen","year":"2020","unstructured":"Chen, R.J., et al.: Pathomic fusion: an integrated framework for fusing histopathology and genomic features for cancer diagnosis and prognosis. IEEE Trans. Med. Imaging 41(4), 757\u2013770 (2020)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"12_CR6","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":"12_CR7","doi-asserted-by":"crossref","unstructured":"Chen, W., Si, C., Zhang, Z., Wang, L., Wang, Z., Tan, T.: Semantic prompt for few-shot image recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 23581\u201323591 (2023)","DOI":"10.1109\/CVPR52729.2023.02258"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Y.C., Lu, C.S.: Rankmix: data augmentation for weakly supervised learning of classifying whole slide images with diverse sizes and imbalanced categories. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 23936\u201323945 (2023)","DOI":"10.1109\/CVPR52729.2023.02292"},{"key":"12_CR9","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1016\/j.media.2019.03.009","volume":"54","author":"V Cheplygina","year":"2019","unstructured":"Cheplygina, V., de Bruijne, M., Pluim, J.P.: Not-so-supervised: a survey of semi-supervised, multi-instance, and transfer learning in medical image analysis. Med. Image Anal. 54, 280\u2013296 (2019)","journal-title":"Med. Image Anal."},{"key":"12_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1007\/978-3-030-59722-1_50","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020","author":"P Chikontwe","year":"2020","unstructured":"Chikontwe, P., Kim, M., Nam, S.J., Go, H., Park, S.H.: Multiple instance learning with center embeddings for histopathology classification. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12265, pp. 519\u2013528. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59722-1_50"},{"key":"12_CR11","unstructured":"Gu, J., et al.: A systematic survey of prompt engineering on vision-language foundation models. arXiv preprint arXiv:2307.12980 (2023)"},{"key":"12_CR12","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3852\u20133861 (2020)","DOI":"10.1109\/CVPR42600.2020.00391"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Huang, Y., Zhao, W., Wang, S., Fu, Y., Jiang, Y., Yu, L.: Conslide: asynchronous hierarchical interaction transformer with breakup-reorganize rehearsal for continual whole slide image analysis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 21349\u201321360 (2023)","DOI":"10.1109\/ICCV51070.2023.01952"},{"key":"12_CR14","doi-asserted-by":"crossref","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. 1\u201310 (2023)","DOI":"10.1101\/2023.03.29.534834"},{"key":"12_CR15","unstructured":"Ikezogwo, W., et al.: Quilt-1m: one million image-text pairs for histopathology. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 36 (2024)"},{"key":"12_CR16","unstructured":"Ilse, M., Tomczak, J., Welling, M.: Attention-based deep multiple instance learning. In: International Conference on Machine Learning (ICML), pp. 2127\u20132136. PMLR (2018)"},{"key":"12_CR17","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1007\/978-3-031-19827-4_41","volume-title":"ECCV 2022","author":"M Jia","year":"2022","unstructured":"Jia, M., et al.: Visual prompt tuning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13693, pp. 709\u2013727. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19827-4_41"},{"key":"12_CR18","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 (CVPR), pp. 14318\u201314328 (2021)","DOI":"10.1109\/CVPR46437.2021.01409"},{"key":"12_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1007\/978-3-030-87237-3_20","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"H Li","year":"2021","unstructured":"Li, H., et al.: DT-MIL: deformable transformer for\u00a0multi-instance learning on\u00a0histopathological image. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12908, pp. 206\u2013216. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87237-3_20"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Li, H., et al.: Task-specific fine-tuning via variational information bottleneck for weakly-supervised pathology whole slide image classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7454\u20137463 (2023)","DOI":"10.1109\/CVPR52729.2023.00720"},{"key":"12_CR21","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning (ICML), pp. 12888\u201312900. PMLR (2022)"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Lin, T., Xu, H., Yang, C., Xu, Y.: Interventional multi-instance learning with deconfounded instance-level prediction. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), vol.\u00a036, pp. 1601\u20131609 (2022)","DOI":"10.1609\/aaai.v36i2.20051"},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Lin, T., Yu, Z., Hu, H., Xu, Y., Chen, C.W.: Interventional bag multi-instance learning on whole-slide pathological images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 19830\u201319839 (2023)","DOI":"10.1109\/CVPR52729.2023.01899"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"Lu, M.Y., et al.: Visual language pretrained multiple instance zero-shot transfer for histopathology images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 19764\u201319775 (2023)","DOI":"10.1109\/CVPR52729.2023.01893"},{"issue":"6","key":"12_CR25","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":"12_CR26","doi-asserted-by":"crossref","unstructured":"Qu, L., Liu, S., Liu, X., Wang, M., Song, Z.: Towards label-efficient automatic diagnosis and analysis: a comprehensive survey of advanced deep learning-based weakly-supervised, semi-supervised and self-supervised techniques in histopathological image analysis. Phys. Med. Biol. (2022)","DOI":"10.1088\/1361-6560\/ac910a"},{"key":"12_CR27","unstructured":"Qu, L., Luo, X., 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. arXiv preprint arXiv:2305.17891 (2023)"},{"key":"12_CR28","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1007\/978-3-031-16434-7_3","volume-title":"MICCAI 2022","author":"L Qu","year":"2022","unstructured":"Qu, L., Luo, X., Liu, S., Wang, M., Song, Z.: DGMIL: distribution guided multiple instance learning for whole slide image classification. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds.) MICCAI 2022. LNCS, vol. 13432, pp. 24\u201334. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-16434-7_3"},{"key":"12_CR29","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (ICML), pp. 8748\u20138763. PMLR (2021)"},{"key":"12_CR30","unstructured":"Rony, J., Belharbi, S., Dolz, J., Ayed, I.B., McCaffrey, L., Granger, E.: Deep weakly-supervised learning methods for classification and localization in histology images: a survey. arXiv preprint arXiv:1909.03354 (2019)"},{"key":"12_CR31","unstructured":"Shao, Z., et al.: Transmil: transformer based correlated multiple instance learning for whole slide image classification. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 34, pp. 2136\u20132147 (2021)"},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"Shi, X., Xing, F., Xie, Y., Zhang, Z., Cui, L., Yang, L.: Loss-based attention for deep multiple instance learning. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), vol.\u00a034, pp. 5742\u20135749 (2020)","DOI":"10.1609\/aaai.v34i04.6030"},{"key":"12_CR33","doi-asserted-by":"crossref","unstructured":"Song, A.H., et al.: Artificial intelligence for digital and computational pathology. Nat. Rev. Bioeng. 1\u201320 (2023)","DOI":"10.1038\/s44222-023-00096-8"},{"key":"12_CR34","unstructured":"Tu, C., Zhang, Y., Ning, Z.: Dual-curriculum contrastive multi-instance learning for cancer prognosis analysis with whole slide images. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 35, pp. 29484\u201329497 (2022)"},{"key":"12_CR35","unstructured":"Wang, X., et al.: SCL-WC: cross-slide contrastive learning for weakly-supervised whole-slide image classification. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 35, pp. 18009\u201318021 (2022)"},{"key":"12_CR36","doi-asserted-by":"crossref","unstructured":"Wasim, S.T., Naseer, M., Khan, S., Khan, F.S., Shah, M.: Vita-clip: video and text adaptive clip via multimodal prompting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 23034\u201323044 (2023)","DOI":"10.1109\/CVPR52729.2023.02206"},{"key":"12_CR37","doi-asserted-by":"crossref","unstructured":"Xu, G., et al.: Camel: a weakly supervised learning framework for histopathology image segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 10682\u201310691 (2019)","DOI":"10.1109\/ICCV.2019.01078"},{"key":"12_CR38","doi-asserted-by":"crossref","unstructured":"Yao, H., Zhang, R., Xu, C.: Visual-language prompt tuning with knowledge-guided context optimization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6757\u20136767 (2023)","DOI":"10.1109\/CVPR52729.2023.00653"},{"key":"12_CR39","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101789","volume":"65","author":"J Yao","year":"2020","unstructured":"Yao, J., Zhu, X., Jonnagaddala, J., Hawkins, N., Huang, J.: Whole slide images based cancer survival prediction using attention guided deep multiple instance learning networks. Med. Image Anal. 65, 101789 (2020)","journal-title":"Med. Image Anal."},{"key":"12_CR40","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 (CVPR), pp. 18802\u201318812 (2022)","DOI":"10.1109\/CVPR52688.2022.01824"},{"key":"12_CR41","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1007\/978-3-031-43904-9_27","volume-title":"MICCAI 2023","author":"Y Zhang","year":"2023","unstructured":"Zhang, Y., et al.: Text-guided foundation model adaptation for pathological image classification. In: Greenspan, H., et al. (eds.) MICCAI 2023. LNCS, vol. 14224, pp. 272\u2013282. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-43904-9_27"},{"issue":"9","key":"12_CR42","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. Int. J. Comput. Vision 130(9), 2337\u20132348 (2022)","journal-title":"Int. J. Comput. Vision"},{"key":"12_CR43","doi-asserted-by":"crossref","unstructured":"Zhu, X., Yao, J., Zhu, F., Huang, J.: WSISA: making survival prediction from whole slide histopathological images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7234\u20137242 (2017)","DOI":"10.1109\/CVPR.2017.725"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73247-8_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T12:06:45Z","timestamp":1730376405000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73247-8_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9783031732461","9783031732478"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73247-8_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}