{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T15:02:12Z","timestamp":1786978932250,"version":"build-2736575974"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032234957","type":"print"},{"value":"9783032234964","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-3-032-23496-4_5","type":"book-chapter","created":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T22:11:41Z","timestamp":1780351901000},"page":"64-87","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Medal S: Spatio-Textual Prompt Model for\u00a0Medical Segmentation"],"prefix":"10.1007","author":[{"given":"Pengcheng","family":"Shi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaqi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinglin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,1]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Avrahami, O., et al.: Spatext: Spatio-textual representation for controllable image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18370\u201318380 (2023)","DOI":"10.1109\/CVPR52729.2023.01762"},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Bassi, P.R., et\u00a0al.: Radgpt: Constructing 3D image-text tumor datasets. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 23720\u201323730 (2025)","DOI":"10.1109\/ICCV51701.2025.02202"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213\u2013229. Springer (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"5_CR4","unstructured":"Cheng, B., Schwing, A., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. Adv. Neural. Inf. Process. Syst. 34, 17864\u201317875 (2021)"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Du, Y., Bai, F., Huang, T., Zhao, B.: Segvol: Universal and interactive volumetric medical image segmentation. In: Advances in Neural Information Processing Systems, vol.\u00a037, pp. 110746\u2013110783 (2024)","DOI":"10.52202\/079017-3516"},{"key":"5_CR6","unstructured":"Fabian, I., et al..: nninteractive: Redefining 3D promptable segmentation. arXiv preprint arXiv:2503.08373 (2025)"},{"key":"5_CR7","doi-asserted-by":"publisher","unstructured":"Gafni, O., Polyak, A., Ashual, O., Sheynin, S., Parikh, D., Taigman, Y.: Make-a-scene: Scene-based text-to-image generation with human priors. In: European Conference on Computer Vision, pp. 89\u2013106. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-19784-0_6","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"5_CR8","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"He, Y., et al.: VISTA3D: A unified segmentation foundation model for 3D medical imaging. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision and Pattern Recognition (2024)","DOI":"10.1109\/CVPR52734.2025.01943"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Huang, Z., Jiang, Y., Zhang, R., Zhang, S., Zhang, X.: Cat: coordinating anatomical-textual prompts for multi-organ and tumor segmentation. In: Globerson, A., et al., (eds.) Advances in Neural Information Processing Systems, vol.\u00a037, pp. 3588\u20133610 (2024)","DOI":"10.52202\/079017-0119"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Isensee, F., Jaeger, P.F., Kohl, S.A., Petersen, J., Maier-Hein, K.H.: nnu-net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods 18(2), 203\u2013211 (2021)","DOI":"10.1038\/s41592-020-01008-z"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Kikinis, R., Pieper, S.D., Vosburgh, K.G.: 3D Slicer: a platform for subject-specific image analysis, visualization, and clinical support, pp. 277\u2013289. Springer (2013)","DOI":"10.1007\/978-1-4614-7657-3_19"},{"key":"5_CR13","unstructured":"Kirillov, A., et al.: Segment anything. In: Proceedings of the International Conference on Computer Vision, pp. 4015\u20134026 (2023)"},{"key":"5_CR14","unstructured":"Li, W., et\u00a0al.: Scalemai: Accelerating the development of trusted datasets and ai models. arXiv preprint arXiv:2501.03410 (2025)"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Liu, J., et al.: Clip-driven universal model for organ segmentation and tumor detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 21152\u201321164 (2023)","DOI":"10.1109\/ICCV51070.2023.01934"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Ma, J., He, Y., Li, F., Han, L., You, C., Wang, B.: Segment anything in medical images. Nat. Commun. 15, 654 (2024)","DOI":"10.1038\/s41467-024-44824-z"},{"key":"5_CR17","unstructured":"Ma, J., et al.: Efficient medsams: Segment anything in medical images on laptop. arXiv:2412.16085 (2024)"},{"key":"5_CR18","unstructured":"Ma, J., et al.: Medsam2: Segment anything in 3d medical images and videos. arXiv preprint arXiv:2504.03600 (2025)"},{"key":"5_CR19","unstructured":"Ravi, N., et al.: Sam 2: Segment anything in images and videos. In: International Conference on Learning Representations (2025)"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 234\u2013241 (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"5_CR21","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Wang, H., et\u00a0al.: Sam-med3d: towards general-purpose segmentation models for volumetric medical images. In: European Conference on Computer Vision, pp. 51\u201367. Springer (2024)","DOI":"10.1007\/978-3-031-91721-9_4"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Wong, H.E., Rakic, M., Guttag, J., Dalca, A.V.: Scribbleprompt: fast and flexible interactive segmentation for any biomedical image. In: European Conference on Computer Vision, pp. 207\u2013229. Springer (2024)","DOI":"10.1007\/978-3-031-73661-2_12"},{"key":"5_CR24","doi-asserted-by":"crossref","unstructured":"Xu, Z., et al.: Codabench: Flexible, easy-to-use, and reproducible meta-benchmark platform. Patterns 3(7), 100543 (2022)","DOI":"10.1016\/j.patter.2022.100543"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"5_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, X., et al.: Development of a large-scale grounded vision language dataset for chest CT analysis. Sci. Data 12(1), 1636 (2025)","DOI":"10.1038\/s41597-025-05922-9"},{"key":"5_CR27","doi-asserted-by":"crossref","unstructured":"Zhao, T., et al.: A foundation model for joint segmentation, detection and recognition of biomedical objects across nine modalities. Nat. Methods 22, 166\u2013176 (2025)","DOI":"10.1038\/s41592-024-02499-w"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Zhao, Z., et al.: Large-vocabulary segmentation for medical images with text prompts. NPJ Digital Med. 8(1), 566 (2025)","DOI":"10.1038\/s41746-025-01964-w"}],"container-title":["Lecture Notes in Computer Science","Foundation Models for 3D Biomedical Image Segmentation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-23496-4_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T22:11:50Z","timestamp":1780351910000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-23496-4_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032234957","9783032234964"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-23496-4_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"1 May 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MedSegFM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Challenge on Foundation Models for 3D Biomedical Image Segmentation","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nashville","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","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":"11 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"medsegfm2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/openreview.net\/group?id=thecvf.com\/CVPR\/2025\/Workshop\/MedSegFM#tab-active-submissions","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}