{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T10:26:04Z","timestamp":1781519164103,"version":"3.54.1"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032051264","type":"print"},{"value":"9783032051271","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\/978-3-032-05127-1_39","type":"book-chapter","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T21:16:35Z","timestamp":1758316595000},"page":"402-412","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Pre-trained LLM is a\u00a0Semantic-Aware and\u00a0Generalizable Segmentation Booster"],"prefix":"10.1007","author":[{"given":"Fenghe","family":"Tang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenxin","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyang","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaodong","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zihang","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaohua Kevin","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,20]]},"reference":[{"key":"39_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2019.104863","volume":"28","author":"W Al-Dhabyani","year":"2020","unstructured":"Al-Dhabyani, W., Gomaa, M., Khaled, H., Fahmy, A.: Dataset of breast ultrasound images. Data Brief 28, 104863 (2020)","journal-title":"Data Brief"},{"key":"39_CR2","doi-asserted-by":"crossref","unstructured":"Cao, H., et al.: Swin-unet: unet-like pure transformer for medical image segmentation. In: ECCV, pp. 205\u2013218. Springer (2022)","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"39_CR3","unstructured":"Chen, H., et al.: Understanding and mitigating the label noise in pre-training on downstream tasks. arXiv preprint arXiv:2309.17002 (2023)"},{"key":"39_CR4","unstructured":"Chen, J., et al.: Transunet: transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306 (2021)"},{"key":"39_CR5","doi-asserted-by":"crossref","unstructured":"Chen, J., Chen, R., Wang, W., Cheng, J., Zhang, L., Chen, L.: Tinyu-net: lighter yet better u-net with cascaded multi-receptive fields. In: MICCAI, pp. 626\u2013635. Springer (2024)","DOI":"10.1007\/978-3-031-72114-4_60"},{"key":"39_CR6","unstructured":"Codella, N., et al.: Skin lesion analysis toward melanoma detection 2018: a challenge hosted by the international skin imaging collaboration (ISIC). arXiv preprint arXiv:1902.03368 (2019)"},{"key":"39_CR7","doi-asserted-by":"crossref","unstructured":"Ding, X., et al.: Unireplknet: a universal perception large-kernel convnet for audio video point cloud time-series and image recognition. In: CVPR, pp. 5513\u20135524 (2024)","DOI":"10.1109\/CVPR52733.2024.00527"},{"key":"39_CR8","unstructured":"Dosovitskiy, A.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"39_CR9","unstructured":"Dubey, A., et al.: The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)"},{"key":"39_CR10","unstructured":"Guo, D., et al.: Deepseek-r1: incentivizing reasoning capability in LLMs via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)"},{"key":"39_CR11","doi-asserted-by":"crossref","unstructured":"Hatamizadeh, A., et al.: Unetr: transformers for 3D medical image segmentation. In: WACV, pp. 574\u2013584 (2022)","DOI":"10.1109\/WACV51458.2022.00181"},{"issue":"5","key":"39_CR12","first-page":"1484","volume":"42","author":"X Huang","year":"2022","unstructured":"Huang, X., Deng, Z., Li, D., Yuan, X., Fu, Y.: Missformer: an effective transformer for 2D medical image segmentation. TMI 42(5), 1484\u20131494 (2022)","journal-title":"TMI"},{"key":"39_CR13","unstructured":"Jiang, J., Liu, Y.: Can frozen transformers in large language models help with medical image segmentation? In: Medical Imaging with Deep Learning (2024)"},{"key":"39_CR14","unstructured":"Landman, B., Xu, Z., Igelsias, J., Styner, M., Langerak, T., Klein, A.: MICCAI multi-atlas labeling beyond the cranial vault\u2013workshop and challenge. In: Proceedings of MICCAI Challenge, vol.\u00a05, p.\u00a012 (2015)"},{"key":"39_CR15","unstructured":"Lee, H.H., Bao, S., Huo, Y., Landman, B.A.: 3D UX-Net: a large kernel volumetric convnet modernizing hierarchical transformer for medical image segmentation. In: ICLR (2022)"},{"key":"39_CR16","doi-asserted-by":"crossref","unstructured":"Li, C., et al.: Llava-med: training a large language-and-vision assistant for biomedicine in one day. In: NeurIPS, vol. 36 (2024)","DOI":"10.32388\/VLXB6M"},{"key":"39_CR17","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: ICML, pp. 19730\u201319742. PMLR (2023)"},{"key":"39_CR18","first-page":"1","volume":"71","author":"A Lin","year":"2022","unstructured":"Lin, A., Chen, B., Xu, J., Zhang, Z., Lu, G., Zhang, D.: DS-TransUNet: dual swin transformer U-Net for medical image segmentation. TIM 71, 1\u201315 (2022)","journal-title":"TIM"},{"key":"39_CR19","doi-asserted-by":"crossref","unstructured":"Ma, W., Yao, Q., Zhang, X., Huang, Z., Jiang, Z., Zhou, S.K.: Towards accurate unified anomaly segmentation. arXiv preprint arXiv:2501.12295 (2025)","DOI":"10.1109\/WACV61041.2025.00138"},{"key":"39_CR20","unstructured":"Pang, Z., Xie, Z., Man, Y., Wang, Y.X.: Frozen transformers in language models are effective visual encoder layers. arXiv preprint arXiv:2310.12973 (2023)"},{"key":"39_CR21","doi-asserted-by":"crossref","unstructured":"Parkhi, O.M., Vedaldi, A., Zisserman, A., Jawahar, C.: Cats and dogs. In: CVPR, pp. 3498\u20133505. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"39_CR22","doi-asserted-by":"crossref","unstructured":"Pedraza, L., Vargas, C., Narv\u00e1ez, F., Dur\u00e1n, O., Mu\u00f1oz, E., Romero, E.: An open access thyroid ultrasound image database. In: 10th International Symposium on Medical Information Processing and Analysis, vol.\u00a09287, pp. 188\u2013193. SPIE (2015)","DOI":"10.1117\/12.2073532"},{"key":"39_CR23","doi-asserted-by":"crossref","unstructured":"Pogorelov, K., et al.: Kvasir: a multi-class image dataset for computer aided gastrointestinal disease detection. In: ACMMM, pp. 164\u2013169 (2017)","DOI":"10.1145\/3083187.3083212"},{"key":"39_CR24","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: MICCAI, pp. 234\u2013241. Springer (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"39_CR25","unstructured":"Roy, O., Vetterli, M.: The effective rank: a measure of effective dimensionality. In: 2007 15th European Signal Processing Conference, pp. 606\u2013610. IEEE (2007)"},{"key":"39_CR26","doi-asserted-by":"crossref","unstructured":"Roy, S., et al.: Mednext: transformer-driven scaling of convnets for medical image segmentation. In: MICCAI, pp. 405\u2013415. Springer (2023)","DOI":"10.1007\/978-3-031-43901-8_39"},{"key":"39_CR27","doi-asserted-by":"crossref","unstructured":"Tang, F., Ding, J., Quan, Q., Wang, L., Ning, C., Zhou, S.K.: Cmunext: an efficient medical image segmentation network based on large kernel and skip fusion. In: ISBI, pp.\u00a01\u20135. IEEE (2024)","DOI":"10.1109\/ISBI56570.2024.10635609"},{"key":"39_CR28","unstructured":"Tang, F., et al.: Mobileutr: revisiting the relationship between light-weight CNN and transformer for efficient medical image segmentation. arXiv preprint arXiv:2312.01740 (2023)"},{"key":"39_CR29","doi-asserted-by":"crossref","unstructured":"Tang, F., et al.: Mambamim: pre-training mamba with state space token interpolation and its application to medical image segmentation. Med. Image Anal. 103606 (2025)","DOI":"10.1016\/j.media.2025.103606"},{"key":"39_CR30","doi-asserted-by":"crossref","unstructured":"Tang, F., et al.: Hyspark: hybrid sparse masking for large scale medical image pre-training. In: MICCAI, pp. 330\u2013340. Springer (2024)","DOI":"10.1007\/978-3-031-72120-5_31"},{"key":"39_CR31","doi-asserted-by":"crossref","unstructured":"Tang, F., Yao, Q., Ma, W., Wu, C., Jiang, Z., Zhou, S.K.: Hi-end-MAE: hierarchical encoder-driven masked autoencoders are stronger vision learners for medical image segmentation. arXiv preprint arXiv:2502.08347 (2025)","DOI":"10.1016\/j.media.2025.103770"},{"key":"39_CR32","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":"39_CR33","doi-asserted-by":"crossref","unstructured":"Valanarasu, J.M.J., Patel, V.M.: Unext: MLP-based rapid medical image segmentation network. In: MICCAI, pp. 23\u201333. Springer (2022)","DOI":"10.1007\/978-3-031-16443-9_3"},{"key":"39_CR34","doi-asserted-by":"crossref","unstructured":"Wang, H., Cao, P., Wang, J., Zaiane, O.R.: Uctransnet: rethinking the skip connections in U-net from a channel-wise perspective with transformer. In: AAAI, vol.\u00a036, pp. 2441\u20132449 (2022)","DOI":"10.1609\/aaai.v36i3.20144"},{"key":"39_CR35","unstructured":"Wang, R., et al.: ECAMP: entity-centered context-aware medical vision language pre-training. arXiv preprint arXiv:2312.13316 (2023)"},{"key":"39_CR36","unstructured":"Xue, Y., Whitecross, K., Mirzasoleiman, B.: Investigating why contrastive learning benefits robustness against label noise. In: ICML, pp. 24851\u201324871. PMLR (2022)"},{"issue":"6","key":"39_CR37","first-page":"1856","volume":"39","author":"Z Zhou","year":"2019","unstructured":"Zhou, Z., Siddiquee, M.M.R., Tajbakhsh, N., Liang, J.: UNet++: redesigning skip connections to exploit multiscale features in image segmentation. TMI 39(6), 1856\u20131867 (2019)","journal-title":"TMI"}],"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\/978-3-032-05127-1_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T21:16:44Z","timestamp":1758316604000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-05127-1_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,20]]},"ISBN":["9783032051264","9783032051271"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-05127-1_39","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":"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":"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"}}]}}