{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T21:58:52Z","timestamp":1790287132582,"version":"4.1.0"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032382320","type":"print"},{"value":"9783032382337","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T00:00:00Z","timestamp":1790294400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T00:00:00Z","timestamp":1790294400000},"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":[[2027]]},"DOI":"10.1007\/978-3-032-38233-7_15","type":"book-chapter","created":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T21:00:26Z","timestamp":1790283626000},"page":"156-166","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["EndoVLM: An Endoscopy Vision-Language Pre-training Model via\u00a0Anatomy-Guided Sparsity and\u00a0Progressive Alignment"],"prefix":"10.1007","author":[{"given":"Zhenyu","family":"Yi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianwei","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongwei","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sijing","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Lv","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ling","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingda","family":"Xia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,25]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Bernal, J., S\u00e1nchez, F.J., Fern\u00e1ndez-Esparrach, G., Gil, D., Rodr\u00edguez, C., Vilari\u00f1o, F.: Wm-dova maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physicians. Comput. Med. Imaging Graph. 43, 99\u2013111 (2015)","DOI":"10.1016\/j.compmedimag.2015.02.007"},{"key":"15_CR2","unstructured":"Bommasani, R., et\u00a0al.: On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258 (2021)"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Borgli, H., Thambawita, V., Smedsrud, P.H., et al.: Hyperkvasir, a comprehensive multi-class image and video dataset for gastrointestinal endoscopy. Sci. data 7(1), 283 (2020)","DOI":"10.1038\/s41597-020-00622-y"},{"key":"15_CR4","unstructured":"Dermyer, P., Kalra, A., Schwartz, M.: Endodino: A foundation model for gi endoscopy. arXiv preprint arXiv:2501.05488 (2025)"},{"key":"15_CR5","unstructured":"Dong, B., Wang, W., Fan, D.P., Li, J., Fu, H., Shao, L.: Polyp-pvt: Polyp segmentation with pyramid vision transformers. arXiv preprint arXiv:2108.06932 (2021)"},{"key":"15_CR6","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"15_CR7","doi-asserted-by":"publisher","unstructured":"Fu, R., Hu, S., Zheng, X., Tang, C., Liu, X.: Polymamba: Spatial-prior guided mamba for polyp segmentation with high-frequency enhancement. In: MICCAI, pp. 455\u2013465. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-032-05141-7_44","DOI":"10.1007\/978-3-032-05141-7_44"},{"issue":"1","key":"15_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3458754","volume":"3","author":"Y Gu","year":"2021","unstructured":"Gu, Y., Tinn, R., Cheng, H., et al.: Domain-specific language model pretraining for biomedical natural language processing. ACM Trans. Comput. Healthc. 3(1), 1\u201323 (2021)","journal-title":"ACM Trans. Comput. Healthc."},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: CVPR, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Hu, Q., et al.: Monobox: Tightness-free box-supervised polyp segmentation using monotonicity constraint. In: AAAI, vol.\u00a039, pp. 3572\u20133580 (2025)","DOI":"10.1609\/aaai.v39i4.32371"},{"key":"15_CR11","doi-asserted-by":"publisher","unstructured":"Hu, Q., Yi, Z., Zhou, Y., Peng, F., Liu, M., Li, Q., Wang, Z.: Sali: Short-term alignment and long-term interaction network for colonoscopy video polyp segmentation. In: MICCAI, pp. 531\u2013541. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72089-5_50","DOI":"10.1007\/978-3-031-72089-5_50"},{"key":"15_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1007\/978-3-030-37734-2_37","volume-title":"MultiMedia Modeling","author":"D Jha","year":"2020","unstructured":"Jha, D., et al.: Kvasir-SEG: A Segmented Polyp Dataset. In: Ro, Y.M., et al. (eds.) MMM 2020. LNCS, vol. 11962, pp. 451\u2013462. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-37734-2_37"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Jong, M.R., Boers, T.G., Fockens, K.N.: Gastronet-5m: A multicenter dataset for developing foundation models in gastrointestinal endoscopy. Gastroenterology (2025)","DOI":"10.1055\/s-0045-1805427"},{"key":"15_CR14","first-page":"28541","volume":"36","author":"C Li","year":"2023","unstructured":"Li, C., et al.: Llava-med: Training a large language-and-vision assistant for biomedicine in one day. NeurIPS 36, 28541\u201328564 (2023)","journal-title":"NeurIPS"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Miech, A., Alayrac, J.B., Smaira, L., Laptev, I., Sivic, J., Zisserman, A.: End-to-end learning of visual representations from uncurated instructional videos. In: CVPR, pp. 9879\u20139889 (2020)","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"15_CR16","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"15_CR17","unstructured":"Oquab, M., Darcet, T., Moutakanni, T.: Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"issue":"9","key":"15_CR18","doi-asserted-by":"publisher","first-page":"1431","DOI":"10.1093\/ibd\/izac226","volume":"29","author":"G Polat","year":"2023","unstructured":"Polat, G., Kani, H.T., Ergenc, I., Ozen Alahdab, Y., Temizel, A., Atug, O.: Improving the computer-aided estimation of ulcerative colitis severity according to mayo endoscopic score by using regression-based deep learning. Inflamm. Bowel Dis. 29(9), 1431\u20131439 (2023)","journal-title":"Inflamm. Bowel Dis."},{"key":"15_CR19","unstructured":"Radford, A., Kim, J.W., Hallacy, C., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763. PMLR (2021)"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Ruan, J., Li, J., Xiang, S.: Vm-unet: Vision mamba unet for medical image segmentation. ACM Trans. Multimedia Comput. Commun. Appl. (2024)","DOI":"10.1145\/3767748"},{"key":"15_CR21","unstructured":"Shui, Z., et\u00a0al.: Large-scale and fine-grained vision-language pre-training for enhanced ct image understanding. arXiv preprint arXiv:2501.14548 (2025)"},{"issue":"2","key":"15_CR22","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1007\/s11548-013-0926-3","volume":"9","author":"J Silva","year":"2014","unstructured":"Silva, J., Histace, A., Romain, O., Dray, X., Granado, B.: Toward embedded detection of polyps in wce images for early diagnosis of colorectal cancer. Int. J. Comput. Assist. Radiol. Surg. 9(2), 283\u2013293 (2014)","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"15_CR23","unstructured":"Sim\u00e9oni, O., et\u00a0al.: Dinov3. arXiv preprint arXiv:2508.10104 (2025)"},{"issue":"2","key":"15_CR24","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1109\/TMI.2015.2487997","volume":"35","author":"N Tajbakhsh","year":"2015","unstructured":"Tajbakhsh, N., Gurudu, S.R., Liang, J.: Automated polyp detection in colonoscopy videos using shape and context information. IEEE Trans. Med. Imaging 35(2), 630\u2013644 (2015)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Tang, Y., et al.: Self-supervised pre-training of swin transformers for 3d medical image analysis. In: CVPR, pp. 20730\u201320740 (2022)","DOI":"10.1109\/CVPR52688.2022.02007"},{"key":"15_CR26","doi-asserted-by":"publisher","unstructured":"Tian, Q., et al.: Endomamba: an efficient foundation model for endoscopic videos via hierarchical pre-training. In: MICCAI, pp. 224\u2013234. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-032-05114-1_22","DOI":"10.1007\/978-3-032-05114-1_22"},{"key":"15_CR27","doi-asserted-by":"publisher","unstructured":"Tian, Y., et al.: Contrastive transformer-based multiple instance learning for weakly supervised polyp frame detection. In: MICCAI, pp. 88\u201398. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-16437-8_9","DOI":"10.1007\/978-3-031-16437-8_9"},{"issue":"12","key":"15_CR28","doi-asserted-by":"publisher","first-page":"1399","DOI":"10.1038\/s41551-022-00936-9","volume":"6","author":"E Tiu","year":"2022","unstructured":"Tiu, E., et al.: Expert-level detection of pathologies from unannotated chest x-ray images via self-supervised learning. Nat. Biomed. Eng. 6(12), 1399\u20131406 (2022)","journal-title":"Nat. Biomed. Eng."},{"issue":"1","key":"15_CR29","first-page":"4037190","volume":"2017","author":"D V\u00e1zquez","year":"2017","unstructured":"V\u00e1zquez, D., et al.: A benchmark for endoluminal scene segmentation of colonoscopy images. J. Healthc. Eng. 2017(1), 4037190 (2017)","journal-title":"J. Healthc. Eng."},{"key":"15_CR30","doi-asserted-by":"publisher","unstructured":"Wang, R., et\u00a0al.: Simcrop: Radiograph representation learning with similarity-driven cross-granularity pre-training. In: MICCAI, pp. 563\u2013573. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-032-04971-1_53","DOI":"10.1007\/978-3-032-04971-1_53"},{"issue":"8035","key":"15_CR31","doi-asserted-by":"publisher","first-page":"970","DOI":"10.1038\/s41586-024-07894-z","volume":"634","author":"X Wang","year":"2024","unstructured":"Wang, X., et al.: A pathology foundation model for cancer diagnosis and prognosis prediction. Nature 634(8035), 970\u2013978 (2024)","journal-title":"Nature"},{"key":"15_CR32","doi-asserted-by":"publisher","unstructured":"Wang, Z., Liu, C., Zhang, S., Dou, Q.: Foundation model for endoscopy video analysis via large-scale self-supervised pre-train. In: MICCAI, pp. 101\u2013111. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-43996-4_10","DOI":"10.1007\/978-3-031-43996-4_10"},{"key":"15_CR33","doi-asserted-by":"crossref","unstructured":"Wang, Z., Liu, C., Zhu, L., Wang, T., Zhang, S., Dou, Q.: Improving foundation model for endoscopy video analysis via representation learning on long sequences. IEEE J. Biomed. Health Inform. (2025)","DOI":"10.1109\/JBHI.2025.3532311"},{"key":"15_CR34","unstructured":"Yang, A., et\u00a0al.: Qwen3 technical report. arXiv preprint arXiv:2505.09388 (2025)"},{"key":"15_CR35","unstructured":"Zhang, S., et\u00a0al.: Biomedclip: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs. arXiv preprint arXiv:2303.00915 (2023)"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-38233-7_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T21:00:30Z","timestamp":1790283630000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-38233-7_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,25]]},"ISBN":["9783032382320","9783032382337"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-38233-7_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,25]]},"assertion":[{"value":"25 September 2026","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","label":"Disclosure of Interests","group":{"name":"EthicsHeading","label":"Ethics"}},{"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":"Strasbourg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 October 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2026\/en\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}