{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T08:06:57Z","timestamp":1788941217257,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":81,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370402","type":"print"},{"value":"9783032370419","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\/978-3-032-37041-9_19","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T07:30:58Z","timestamp":1788939058000},"page":"351-370","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["RAU: Reference-Based Anatomical Understanding with\u00a0Vision Language Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9830-3285","authenticated-orcid":false,"given":"Yiwei","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1069-1215","authenticated-orcid":false,"given":"Yikang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaqi","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheyuan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boris","family":"Mailhe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ankush","family":"Mukherjee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Terrence","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanhui","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"19_CR1","doi-asserted-by":"publisher","unstructured":"Alhadidi, T., Jaber, A., Jaradat, S., Ashqar, H., Elhenawy, M.: Object detection using oriented window learning vision transformer: roadway assets recognition. In: Abdelgawad, A., Jamil, A., Hameed, A.A. (eds.) ISBCom 2024. LNNS, vol. 1268, pp. 506\u2013522. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-82377-0_41","DOI":"10.1007\/978-3-031-82377-0_41"},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Alozai, M.I.: The impact of intraoperative imaging on outcomes in combined neurosurgical and reconstructive procedures: a systematic review. Cureus 17(6), (2025)","DOI":"10.7759\/cureus.86035"},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Antol, S.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433. (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"19_CR4","unstructured":"Bai, J.: Qwen technical report, (2023). arXiv:2309.16609 arXiv preprint"},{"issue":"8","key":"19_CR5","doi-asserted-by":"publisher","first-page":"1788","DOI":"10.1109\/TMI.2019.2897538","volume":"38","author":"G Balakrishnan","year":"2019","unstructured":"Balakrishnan, G., Zhao, A., Sabuncu, M.R., Guttag, J., Dalca, A.V.: Voxelmorph: a learning framework for deformable medical image registration. IEEE Trans. Med. Imaging 38(8), 1788\u20131800 (2019)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"19_CR6","doi-asserted-by":"crossref","unstructured":"Berrezueta, S.: Foundation models for medical image segmentation: a literature review. In: 2025 13th International Symposium on Digital Forensics and Security (ISDFS), pp. 1\u20137. IEEE (2025)","DOI":"10.1109\/ISDFS65363.2025.11012116"},{"issue":"06","key":"19_CR7","doi-asserted-by":"publisher","first-page":"651","DOI":"10.1097\/CM9.0000000000003489","volume":"138","author":"Y Bian","year":"2025","unstructured":"Bian, Y., Li, J., Ye, C., Jia, X., Yang, Q.: Artificial intelligence in medical imaging: From task-specific models to large-scale foundation models. Chin. Med. J. 138(06), 651\u2013663 (2025)","journal-title":"Chin. Med. J."},{"key":"19_CR8","doi-asserted-by":"crossref","unstructured":"Chen, B., Xu, Z., Kirmani, S., Ichter, B., Sadigh, D., Guibas, L., Xia, F.: SpatialVLM: Endowing vision-language models with spatial reasoning capabilities. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14455\u201314465. (2024)","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"19_CR9","doi-asserted-by":"crossref","unstructured":"Chen, J.: Huatuogpt-vision, towards injecting medical visual knowledge into multimodal LLMs at scale, (2024). arXiv:2406.19280 arXiv preprint","DOI":"10.18653\/v1\/2024.emnlp-main.418"},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Chen, X., Lai, Z., Ruan, K., Chen, S., Liu, J., Liu, Z.: R-llava: improving med-vqa understanding through visual region of interest. In: 2025 International Joint Conference on Neural Networks (IJCNN), pp. 1\u201310. IEEE (2025)","DOI":"10.1109\/IJCNN64981.2025.11227685"},{"key":"19_CR11","unstructured":"Cuturi, M.: Sinkhorn distances: lightspeed computation of optimal transport. Adv. Neural. Inf. Process. Syst. 26, (2013)"},{"key":"19_CR12","unstructured":"Dong, G.: How abilities in large language models are affected by supervised fine-tuning data composition, (2023). arXiv:2310.05492 arXiv preprint"},{"key":"19_CR13","unstructured":"Dong, Q.: A survey on in-context learning, (2022). arXiv:2301.00234 arXiv preprint"},{"key":"19_CR14","unstructured":"Dutt, R., Ericsson, L., Sanchez, P., Tsaftaris, S.A., Hospedales, T.M.: Parameter-efficient fine-tuning for medical image analysis: the missed opportunity. In: Proceedings of Medical Imaging with Deep Learning (MIDL), pp. 1\u201320., Paris, France (2024)"},{"issue":"6","key":"19_CR15","doi-asserted-by":"publisher","first-page":"608","DOI":"10.3390\/bioengineering12060608","volume":"12","author":"K Fan","year":"2025","unstructured":"Fan, K., Liang, L., Li, H., Situ, W., Zhao, W., Li, G.: Research on medical image segmentation based on sam and its future prospects. Bioengineering 12(6), 608 (2025)","journal-title":"Bioengineering"},{"issue":"5","key":"19_CR16","doi-asserted-by":"publisher","first-page":"52","DOI":"10.3390\/tomography11050052","volume":"11","author":"Y Gao","year":"2025","unstructured":"Gao, Y., Jiang, Y., Peng, Y., Yuan, F., Zhang, X., Wang, J.: Medical image segmentation: A comprehensive review of deep learning-based methods. Tomography 11(5), 52 (2025)","journal-title":"Tomography"},{"key":"19_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.oraloncology.2024.106979","volume":"157","author":"P Gaudioso","year":"2024","unstructured":"Gaudioso, P., Contro, G., Taboni, S., Costantino, P., Visconti, F., Sozzi, M., Borsetto, D., Sharma, R., De Almeida, J., Verillaud, B., et al.: Intraoperative surgical navigation as a precision medicine tool in Sinonasal and craniofacial oncologic surgery. Oral Oncol. 157, 106979 (2024)","journal-title":"Oral Oncol."},{"key":"19_CR18","unstructured":"Guo, D.: Deepseek-r1: Incentivizing reasoning capability in LLMs via reinforcement learning, (2025). arXiv:2501.12948 arXiv preprint"},{"key":"19_CR19","doi-asserted-by":"publisher","first-page":"1430984","DOI":"10.3389\/frai.2024.1430984","volume":"7","author":"I Hartsock","year":"2024","unstructured":"Hartsock, I., Rasool, G.: Vision-language models for medical report generation and visual question answering: A review. Frontiers in artificial intelligence 7, 1430984 (2024)","journal-title":"Frontiers in artificial intelligence"},{"key":"19_CR20","unstructured":"Hu, M., Qian, J.: Advancing medical imaging with language models. Patterns (2024). review. (). PMC11075180"},{"key":"19_CR21","doi-asserted-by":"publisher","unstructured":"Huang, X.: A refer-and-ground multimodal large language model for biomedicine. In: Linguraru, M.G. (ed.) MICCAI 2024. LNCS, vol. 15012, pp. 399\u2013409. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72390-2_38","DOI":"10.1007\/978-3-031-72390-2_38"},{"key":"19_CR22","doi-asserted-by":"crossref","unstructured":"Huang, X.: Towards a multimodal large language model with pixel-level insight for biomedicine. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, pp. 3779\u20133787. (2025)","DOI":"10.1609\/aaai.v39i4.32394"},{"issue":"2","key":"19_CR23","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","volume":"18","author":"F Isensee","year":"2021","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)","journal-title":"Nat. Methods"},{"key":"19_CR24","doi-asserted-by":"crossref","unstructured":"Jadon, S.: A survey of loss functions for semantic segmentation. In: 2020 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB), pp. 1\u20137. IEEE (2020)","DOI":"10.1109\/CIBCB48159.2020.9277638"},{"key":"19_CR25","unstructured":"Jin, C., Guo, Z., Lin, Y., Luo, L., Chen, H.: Label-efficient deep learning in medical image analysis: challenges and future directions, (2023). arXiv:2303.12484 arXiv preprint"},{"issue":"1","key":"19_CR26","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1038\/s41746-024-01273-8","volume":"7","author":"DZ Khan","year":"2024","unstructured":"Khan, D.Z., Valetopoulou, A., Das, A., Hanrahan, J.G., Williams, S.C., Bano, S., Borg, A., Dorward, N.L., Barbarisi, S., Culshaw, L., et al.: Artificial intelligence assisted operative anatomy recognition in endoscopic pituitary surgery. NPJ Digital Med. 7(1), 314 (2024)","journal-title":"NPJ Digital Med."},{"key":"19_CR27","doi-asserted-by":"crossref","unstructured":"Lai, X.: Lisa: reasoning segmentation via large language model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9579\u20139589. (2024)","DOI":"10.1109\/CVPR52733.2024.00915"},{"issue":"9","key":"19_CR28","doi-asserted-by":"publisher","first-page":"2198","DOI":"10.1109\/TMI.2019.2900516","volume":"38","author":"S Leclerc","year":"2019","unstructured":"Leclerc, S., Smistad, E., Pedrosa, J., \u00d8stvik, A., Cervenansky, F., Espinosa, F., Espeland, T., Berg, E.A.R., Jodoin, P.M., Grenier, T., et al.: Deep learning for segmentation using an open large-scale dataset in 2d echocardiography. IEEE Trans. Med. Imaging 38(9), 2198\u20132210 (2019)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"19_CR29","doi-asserted-by":"publisher","first-page":"28541","DOI":"10.52202\/075280-1240","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. Adv. Neural. Inf. Process. Syst. 36, 28541\u201328564 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR30","doi-asserted-by":"crossref","unstructured":"Li, L.H.: Grounded language-image pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10965\u201310975. (2022)","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"19_CR31","unstructured":"Li, Y.: Echopulse: ECG controlled echocardio-grams video generation, (2024). arXiv:2410.03143 arXiv preprint"},{"key":"19_CR32","doi-asserted-by":"publisher","unstructured":"Lian, C., Zhou, H.Y., Yu, Y., Wang, L.: Less could be better: parameter-efficient fine-tuning advances medical vision foundation models. arXiv preprint arXiv:2401.12215 (2024).https:\/\/doi.org\/10.48550\/arXiv.2401.12215","DOI":"10.48550\/arXiv.2401.12215"},{"key":"19_CR33","unstructured":"Liu, A.: Deepseek-v3 technical report, (2024). arXiv:2412.19437 arXiv preprint"},{"key":"19_CR34","unstructured":"Liu, H.: a survey on hallucination in large vision-language models, (2024). arXiv:2402.00253 arXiv preprint"},{"key":"19_CR35","doi-asserted-by":"publisher","first-page":"34892","DOI":"10.52202\/075280-1516","volume":"36","author":"H Liu","year":"2023","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. Adv. Neural. Inf. Process. Syst. 36, 34892\u201334916 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR36","doi-asserted-by":"publisher","unstructured":"Liu, S., et\u00a0al.: Grounding dino: Marrying dino with grounded pre-training for open-set object detection. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) ECCV 2024. LNCS, vol. 15105, pp. 38\u201355. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72970-6_3","DOI":"10.1007\/978-3-031-72970-6_3"},{"issue":"4","key":"19_CR37","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1093\/jamia\/ocaf008","volume":"32","author":"S Liu","year":"2025","unstructured":"Liu, S., McCoy, A.B., Wright, A.: Improving large language model applications in biomedicine with retrieval-augmented generation: a systematic review, meta-analysis, and clinical development guidelines. J. Am. Med. Inform. Assoc. 32(4), 605\u2013615 (2025). https:\/\/doi.org\/10.1093\/jamia\/ocaf008","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"19_CR38","doi-asserted-by":"publisher","unstructured":"Liu, X., Wang, X., Chen, D., Zhang, H.: Automatic quantitative coronary analysis based on deep learning. Appl. Sci. 13(5) (2023). https:\/\/doi.org\/10.3390\/app13052975, https:\/\/www.mdpi.com\/2076-3417\/13\/5\/2975","DOI":"10.3390\/app13052975"},{"key":"19_CR39","unstructured":"Liu, Y.: Seg-zero: reasoning-chain guided segmentation via cognitive reinforcement, (2025). arXiv:2503.06520 arXiv preprint"},{"key":"19_CR40","doi-asserted-by":"crossref","unstructured":"Liu, Z.: Radiology-GPT: a large language model for radiology, (2025). Meta-Radiol. 100153","DOI":"10.1016\/j.metrad.2025.100153"},{"key":"19_CR41","doi-asserted-by":"publisher","unstructured":"Luo, X., Li, Z., Zhang, S., Liao, W., Wang, G.: Rethinking abdominal organ segmentation (RAOS) in the clinical scenario: a robustness evaluation benchmark with challenging cases. In: Linguraru, M.G., et\u00a0al. (eds.) MICCAI 2024. LNCS, vol. 15009, pp. 531\u2013541. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72114-4_51","DOI":"10.1007\/978-3-031-72114-4_51"},{"issue":"1","key":"19_CR42","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1038\/s41467-024-44824-z","volume":"15","author":"J Ma","year":"2024","unstructured":"Ma, J., He, Y., Li, F., Han, L., You, C., Wang, B.: Segment anything in medical images. Nat. Commun. 15(1), 654 (2024)","journal-title":"Nat. Commun."},{"key":"19_CR43","unstructured":"Ma, J.: Medsam2: segment anything in 3D medical images and videos, (2025). arXiv:2504.03600 arXiv preprint"},{"key":"19_CR44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.media.2016.05.005","volume":"35","author":"S Matl","year":"2017","unstructured":"Matl, S., Brosig, R., Baust, M., Navab, N., Demirci, S.: Vascular image registration techniques: A living review. Med. Image Anal. 35, 1\u201317 (2017)","journal-title":"Med. Image Anal."},{"key":"19_CR45","unstructured":"Moor, M.: Med-flamingo: a multimodal medical few-shot learner. In: Machine Learning for Health (ML4H), pp. 353\u2013367. (2023) PMLR"},{"issue":"10","key":"19_CR46","doi-asserted-by":"publisher","first-page":"900","DOI":"10.3348\/kjr.2025.0599","volume":"26","author":"Y Nam","year":"2025","unstructured":"Nam, Y., et al.: Multimodal large language models in medical imaging: current state and future directions. Korean J. Radiol. 26(10), 900\u2013923 (2025)","journal-title":"Korean J. Radiol."},{"key":"19_CR47","doi-asserted-by":"publisher","unstructured":"Pan, J.: Medvlm-r1: incentivizing medical reasoning capability of vision-language models (VLMs) via reinforcement learning. In: Gee, J.C. (ed.) MICCAI 2025. LNCS, vol. 15966, pp. 337\u2013347. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-032-04981-0_32","DOI":"10.1007\/978-3-032-04981-0_32"},{"issue":"1","key":"19_CR48","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1038\/s41597-023-02871-z","volume":"11","author":"M Popov","year":"2024","unstructured":"Popov, M., et al.: Dataset for automatic region-based coronary artery disease diagnostics using x-ray angiography images. Scientific data 11(1), 20 (2024)","journal-title":"Scientific data"},{"key":"19_CR49","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2024.101540","volume":"49","author":"H Ramadan","year":"2024","unstructured":"Ramadan, H., El Bourakadi, D., Yahyaouy, A., Tairi, H.: Medical image registration in the era of transformers: A recent review. Informatics in Medicine Unlocked 49, 101540 (2024)","journal-title":"Informatics in Medicine Unlocked"},{"key":"19_CR50","unstructured":"Ravi, N.: Sam 2: segment anything in images and videos, (2024). arXiv:2408.00714 arXiv preprint"},{"key":"19_CR51","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2024.101504","volume":"47","author":"ME Rayed","year":"2024","unstructured":"Rayed, M.E., Islam, S.S., Niha, S.I., Jim, J.R., Kabir, M.M., Mridha, M.: Deep learning for medical image segmentation: State-of-the-art advancements and challenges. Informatics in medicine unlocked 47, 101504 (2024)","journal-title":"Informatics in medicine unlocked"},{"key":"19_CR52","doi-asserted-by":"publisher","unstructured":"Serruys, P.W., et al.: Assessment of percutaneous transluminal coronary angioplasty by quantitative coronary angiography: diameter versus densitometric area measurements. Am. J. Cardiol. 54(6), 482\u2013488 (1984). https:\/\/doi.org\/10.1016\/0002-9149(84)90235-2, https:\/\/www.sciencedirect.com\/science\/article\/pii\/0002914984902352","DOI":"10.1016\/0002-9149(84)90235-2"},{"key":"19_CR53","unstructured":"Shao, Z.: Deepseekmath: pushing the limits of mathematical reasoning in open language models, (2024). arXiv:2402.03300 arXiv preprint"},{"issue":"11","key":"19_CR54","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0277693","volume":"17","author":"X Shen","year":"2022","unstructured":"Shen, X., Han, D., Chen, C., Luo, G., Wu, Z.: An effective spatial relational reasoning networks for visual question answering. PLoS ONE 17(11), e0277693 (2022)","journal-title":"PLoS ONE"},{"key":"19_CR55","unstructured":"Stogiannidis, I., McDonagh, S., Tsaftaris, S.A.: Mind the gap: benchmarking spatial reasoning in vision-language models. arXiv preprint arXiv:2503.19707 (2025)"},{"key":"19_CR56","doi-asserted-by":"crossref","unstructured":"Sudre, C.H., Li, W., Vercauteren, T., Ourselin, S., Cardoso, J., M.: Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. In: International Workshop on Deep Learning in Medical Image Analysis, pp. 240\u2013248. Springer (2017)","DOI":"10.1007\/978-3-319-67558-9_28"},{"key":"19_CR57","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1038\/s41591-024-03302-1","volume":"31","author":"R Tanno","year":"2025","unstructured":"Tanno, R., et al.: Collaboration between clinicians and vision-language models in radiology report generation. Nat. Med. 31, 599\u2013608 (2025). https:\/\/doi.org\/10.1038\/s41591-024-03302-1","journal-title":"Nat. Med."},{"key":"19_CR58","doi-asserted-by":"crossref","unstructured":"Tanno, R.: Consensus, dissensus and synergy between clinicians and specialist foundation models in radiology report generation, (2023). arXiv:2311.18260 arXiv preprint","DOI":"10.21203\/rs.3.rs-3940387\/v1"},{"issue":"12","key":"19_CR59","doi-asserted-by":"publisher","first-page":"578","DOI":"10.1038\/s42256-019-0126-0","volume":"1","author":"M Varma","year":"2019","unstructured":"Varma, M., Lu, M., Gardner, R., Dunnmon, J., Khandwala, N., Rajpurkar, P., Long, J., Beaulieu, C., Shpanskaya, K., Fei-Fei, L., et al.: Automated abnormality detection in lower extremity radiographs using deep learning. Nature Machine Intelligence 1(12), 578\u2013583 (2019)","journal-title":"Nature Machine Intelligence"},{"issue":"1","key":"19_CR60","doi-asserted-by":"publisher","first-page":"10704","DOI":"10.1038\/s41598-025-95666-8","volume":"15","author":"M Varol Ar\u0131soy","year":"2025","unstructured":"Varol Ar\u0131soy, M., Ar\u0131soy, A., Uysal, \u0130: A vision attention driven language framework for medical report generation. Sci. Rep. 15(1), 10704 (2025)","journal-title":"Sci. Rep."},{"key":"19_CR61","unstructured":"van Veldhuizen, V., et\u00a0al.: Foundation models in medical imaging\u2013a review and outlook. arXiv preprint arXiv:2506.09095 (2025)"},{"key":"19_CR62","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103201","volume":"95","author":"H Wang","year":"2024","unstructured":"Wang, H., Jin, Q., Li, S., Liu, S., Wang, M., Song, Z.: A comprehensive survey on deep active learning in medical image analysis. Med. Image Anal. 95, 103201 (2024)","journal-title":"Med. Image Anal."},{"issue":"3","key":"19_CR63","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1109\/TPAMI.2012.143","volume":"35","author":"H Wang","year":"2012","unstructured":"Wang, H., Suh, J.W., Das, S.R., Pluta, J.B., Craige, C., Yushkevich, P.A.: Multi-atlas segmentation with joint label fusion. IEEE Trans. Pattern Anal. Mach. Intell. 35(3), 611\u2013623 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"19_CR64","unstructured":"Wang, L.: Interpretable bilingual multimodal large language model for diverse biomedical tasks, (2024). arXiv:2410.18387 arXiv preprint"},{"key":"19_CR65","doi-asserted-by":"crossref","unstructured":"Wang, X., Figueredo, G., Li, R., Zhang, W.E., Chen, W., Chen, X.: A survey of deep-learning-based radiology report generation using multimodal inputs. Med. Image Anal. 103627 (2025)","DOI":"10.1016\/j.media.2025.103627"},{"issue":"5","key":"19_CR66","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.230024","volume":"5","author":"J Wasserthal","year":"2023","unstructured":"Wasserthal, J., et al.: Totalsegmentator: robust segmentation of 104 anatomic structures in CT images. Radiol. Artif. Intell. 5(5), e230024 (2023)","journal-title":"Radiol. Artif. Intell."},{"key":"19_CR67","volume-title":"Exploring the trade-offs: Unified large language models vs local fine-tuned models for highly-specific radiology NLI task","author":"Z Wu","year":"2025","unstructured":"Wu, Z., et al.: Exploring the trade-offs: Unified large language models vs local fine-tuned models for highly-specific radiology NLI task. IEEE Trans, Big Data (2025)"},{"key":"19_CR68","unstructured":"Xia, Y., Pan, Z., Hu, L., Zhu, Z.: MMed-rag: benchmarking RAG for medical multimodal LLMs. In: The Thirteenth International Conference on Learning Representations (ICLR, (2025)"},{"key":"19_CR69","doi-asserted-by":"crossref","unstructured":"Xu, W.: Lingshu: a generalist foundation model for unified multimodal medical understanding and reasoning, (2025). arXiv:2506.07044 arXiv preprint","DOI":"10.1109\/TPAMI.2026.3730310"},{"key":"19_CR70","doi-asserted-by":"crossref","unstructured":"Yan, Z.: Samed-2: selective memory enhanced medical segment anything model, (2025). arXiv:2507.03698 arXiv preprint","DOI":"10.1007\/978-3-032-05169-1_52"},{"key":"19_CR71","doi-asserted-by":"crossref","unstructured":"Yang, R., Ning, Y., Liu, N.: Retrieval-augmented generation for generative artificial intelligence in health care. NPJ Health Syst, (2025). perspective","DOI":"10.1038\/s44401-024-00004-1"},{"key":"19_CR72","unstructured":"Yang, T., Jordan, T., Liu, N., Sun, J.: Common inpainted objects in-n-out of context, (2025). arXiv:2506.00721 arXiv preprint"},{"key":"19_CR73","unstructured":"Yang, T.: Concept-centric token interpretation for vector-quantized generative models, (2025). arXiv:2506.00698 arXiv preprint"},{"issue":"8","key":"19_CR74","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0202950","volume":"13","author":"C Zanchin","year":"2018","unstructured":"Zanchin, C., Yamaji, K., Rogge, C., Lesche, D., Zanchin, T., Ueki, Y., Windecker, S., Mohacsi, P., R\u00e4ber, L., Sigurdardottir, V.: Progression of cardiac allograft vasculopathy assessed by serial three-vessel quantitative coronary angiography. PLoS ONE 13(8), e0202950 (2018)","journal-title":"PLoS ONE"},{"key":"19_CR75","first-page":"823","volume":"35","author":"G Zhang","year":"2022","unstructured":"Zhang, G., Navasardyan, S., Chen, L., Zhao, Y., Wei, Y., Shi, H., et al.: Mask matching transformer for few-shot segmentation. Adv. Neural. Inf. Process. Syst. 35, 823\u2013836 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR76","unstructured":"Zhang, H.: Dino: Detr with improved denoising anchor boxes for end-to-end object detection, (2022). arXiv:2203.03605 arXiv preprint"},{"key":"19_CR77","unstructured":"Zhang, Y.: EVF-SAM: early vision-language fusion for text-prompted segment anything model, (2024). arXiv:2406.20076 arXiv preprint"},{"key":"19_CR78","doi-asserted-by":"crossref","unstructured":"Zhao, C., Xu, Z., Baral, P., Esposito, M., Zhou, W.: Multi-graph graph matching for coronary artery semantic labeling in invasive coronary angiograms, (2025). Pattern Recogn","DOI":"10.1016\/j.patcog.2025.111943"},{"key":"19_CR79","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2025.3568479","volume-title":"Retrieval-augmented few-shot medical image segmentation with foundation models","author":"L Zhao","year":"2025","unstructured":"Zhao, L., Chen, X., Chen, E.Z., Liu, Y., Chen, T., Sun, S.: Retrieval-augmented few-shot medical image segmentation with foundation models. IEEE Trans. Neural Networks Learn, Syst (2025)"},{"issue":"5","key":"19_CR80","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ab6b43","volume":"65","author":"J Zhu","year":"2020","unstructured":"Zhu, J., et al.: Heuristic tree searching for pose-independent 3d\/2d rigid registration of vessel structures. Phys. Med. Biol. 65(5), 055010 (2020)","journal-title":"Phys. Med. Biol."},{"key":"19_CR81","doi-asserted-by":"publisher","first-page":"19769","DOI":"10.52202\/075280-0868","volume":"36","author":"X Zou","year":"2023","unstructured":"Zou, X., Yang, J., Zhang, H., Li, F., Li, L., Wang, J., Wang, L., Gao, J., Lee, Y.J.: Segment everything everywhere all at once. Adv. Neural. Inf. Process. Syst. 36, 19769\u201319782 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37041-9_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T07:31:12Z","timestamp":1788939072000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37041-9_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370402","9783032370419"],"references-count":81,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37041-9_19","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":"10 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","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":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}