{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T10:10:54Z","timestamp":1789035054915,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":54,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032371959","type":"print"},{"value":"9783032371966","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\/978-3-032-37196-6_21","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T09:35:20Z","timestamp":1789032920000},"page":"381-399","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MediRound: Multi-round Entity-Level Reasoning Segmentation in\u00a0Medical Images"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1007-9349","authenticated-orcid":false,"given":"Qinyue","family":"Tong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3579-9130","authenticated-orcid":false,"given":"Ziqian","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4759-2276","authenticated-orcid":false,"given":"Jun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9982-9221","authenticated-orcid":false,"given":"Rui","family":"Zuo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1785-7847","authenticated-orcid":false,"given":"Zhe-Ming","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3775-3877","authenticated-orcid":false,"given":"Yueming","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"21_CR1","unstructured":"Achiam, J., et al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"issue":"1","key":"21_CR2","doi-asserted-by":"publisher","first-page":"4128","DOI":"10.1038\/s41467-022-30695-9","volume":"13","author":"M Antonelli","year":"2022","unstructured":"Antonelli, M.: The medical segmentation decathlon. Nature Commun. 13(1), 4128 (2022)","journal-title":"Nature Commun."},{"key":"21_CR3","unstructured":"Bai, J., et\u00a0al.: Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)"},{"key":"21_CR4","unstructured":"Baid, U., et al.: The RSNA-ASNR-MICCAI BraTs 2021 benchmark on brain tumor segmentation and radiogenomic classification. arXiv preprint arXiv:2107.02314 (2021)"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Cheng, J., et\u00a0al.: Interactive medical image segmentation: A benchmark dataset and baseline. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 20841\u201320851 (2025)","DOI":"10.1109\/CVPR52734.2025.01941"},{"key":"21_CR6","unstructured":"Cheng, J., et\u00a0al.: Sam-med2d. arXiv preprint arXiv:2308.16184 (2023)"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Drozdzal, M., Vorontsov, E., Chartrand, G., Kadoury, S., Pal, C.: The importance of skip connections in biomedical image segmentation. In: International Workshop on Deep Learning in Medical Image Analysis, pp. 179\u2013187. Springer (2016)","DOI":"10.1007\/978-3-319-46976-8_19"},{"key":"21_CR8","doi-asserted-by":"publisher","first-page":"110746","DOI":"10.52202\/079017-3516","volume":"37","author":"Y Du","year":"2024","unstructured":"Du, Y., Bai, F., Huang, T., Zhao, B.: SegVol: Universal and interactive volumetric medical image segmentation. Adv. Neural. Inf. Process. Syst. 37, 110746\u2013110783 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_CR9","unstructured":"Heller, N., et al.: The kits21 challenge: Automatic segmentation of kidneys, renal tumors, and renal cysts in corticomedullary-phase ct. arXiv preprint arXiv:2307.01984 (2023)"},{"issue":"1","key":"21_CR10","doi-asserted-by":"publisher","first-page":"14","DOI":"10.3390\/data5010014","volume":"5","author":"MD Hssayeni","year":"2020","unstructured":"Hssayeni, M.D., Croock, M.S., Salman, A.D., Al-Khafaji, H.F., Yahya, Z.A., Ghoraani, B.: Intracranial hemorrhage segmentation using a deep convolutional model. Data 5(1), 14 (2020)","journal-title":"Data"},{"issue":"4","key":"21_CR11","doi-asserted-by":"publisher","first-page":"1821","DOI":"10.1109\/TMI.2024.3523333","volume":"44","author":"X Huang","year":"2024","unstructured":"Huang, X., Li, H., Cao, M., Chen, L., You, C., An, D.: Cross-modal conditioned reconstruction for language-guided medical image segmentation. IEEE Trans. Med. Imaging 44(4), 1821\u20131835 (2024)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"Huang, X., et al.: Towards a multimodal large language model with pixel-level insight for biomedicine. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a039, pp. 3779\u20133787 (2025)","DOI":"10.1609\/aaai.v39i4.32394"},{"key":"21_CR13","unstructured":"Huang, Y., Peng, Z., Zhao, Y., Yang, P., Yang, X., Shen, W.: MedSeg-R: Reasoning segmentation in medical images with multimodal large language models. arXiv preprint arXiv:2506.10465 (2025)"},{"issue":"2","key":"21_CR14","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"},{"issue":"9","key":"21_CR15","doi-asserted-by":"publisher","first-page":"1228","DOI":"10.1038\/s43018-023-00619-7","volume":"4","author":"DA Jaffray","year":"2023","unstructured":"Jaffray, D.A., Knaul, F., Baumann, M., Gospodarowicz, M.: Harnessing progress in radiotherapy for global cancer control. Nature Cancer 4(9), 1228\u20131238 (2023)","journal-title":"Nature Cancer"},{"key":"21_CR16","unstructured":"Jang, D., Cho, Y., Lee, S., Kim, T., Kim, D.S.: MMR: A large-scale benchmark dataset for multi-target and multi-granularity reasoning segmentation. arXiv preprint arXiv:2503.13881 (2025)"},{"key":"21_CR17","unstructured":"Kirillov, A., et al.: Proceedings of the IEEE\/CVF International Conference on Computer Vision Segment anything, pp. 4015\u20134026 (2023)"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Lai, X., et al.: 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"},{"key":"21_CR19","doi-asserted-by":"publisher","first-page":"28541","DOI":"10.52202\/075280-1240","volume":"36","author":"C Li","year":"2023","unstructured":"Li, C., Wong, C., Zhang, S., Usuyama, N., Liu, H., Yang, J., Naumann, T., Poon, H., Gao, J.: 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."},{"issue":"1","key":"21_CR20","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1109\/TMI.2023.3291719","volume":"43","author":"Z Li","year":"2023","unstructured":"Li, Z., et al.: LViT: language meets vision transformer in medical image segmentation. IEEE Trans. Med. Imaging 43(1), 96\u2013107 (2023)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"21_CR21","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":"21_CR22","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: Marrying DINO with grounded pre-training for open-set object detection. In: European conference on computer vision, pp. 38\u201355. Springer (2024)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"21_CR23","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"L\u00fcddecke, T., Ecker, A.: Image segmentation using text and image prompts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7086\u20137096 (2022)","DOI":"10.1109\/CVPR52688.2022.00695"},{"issue":"1","key":"21_CR25","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."},{"issue":"11","key":"21_CR26","doi-asserted-by":"publisher","first-page":"e815","DOI":"10.1016\/S2589-7500(24)00154-7","volume":"6","author":"J Ma","year":"2024","unstructured":"Ma, J., et al.: Unleashing the strengths of unlabelled data in deep learning-assisted pan-cancer abdominal organ quantification: the flare22 challenge. Lancet Digital Health 6(11), e815\u2013e826 (2024)","journal-title":"Lancet Digital Health"},{"issue":"6","key":"21_CR27","doi-asserted-by":"publisher","first-page":"1749","DOI":"10.1038\/s41591-024-03010-w","volume":"30","author":"V Nauffal","year":"2024","unstructured":"Nauffal, V.: Noninvasive assessment of organ-specific and shared pathways in multi-organ fibrosis using t1 mapping. Nat. Med. 30(6), 1749\u20131760 (2024)","journal-title":"Nat. Med."},{"key":"21_CR28","doi-asserted-by":"crossref","unstructured":"Nie, H., Zheng, Y., Ye, Y., Xie, B.: MTurn-Seg: A large-scale bilingual medical benchmark for multi-turn reasoning segmentation. In: 2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 3946\u20133950. IEEE (2025)","DOI":"10.1109\/BIBM66473.2025.11356076"},{"issue":"3","key":"21_CR29","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1080\/02564602.2014.906861","volume":"31","author":"A Norouzi","year":"2014","unstructured":"Norouzi, A., Rahim, M.S.M., Altameem, A., Saba, T., Rad, A.E., Rehman, A., Uddin, M.: Medical image segmentation methods, algorithms, and applications. IETE Tech. Rev. 31(3), 199\u2013213 (2014)","journal-title":"IETE Tech. Rev."},{"key":"21_CR30","doi-asserted-by":"crossref","unstructured":"Pi, R., Yao, L., Gao, J., Zhang, J., Zhang, T.: Perceptiongpt: Effectively fusing visual perception into LLM. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 27124\u201327133 (2024)","DOI":"10.1109\/CVPR52733.2024.02561"},{"key":"21_CR31","doi-asserted-by":"crossref","unstructured":"Qian, R., Yin, X., Dou, D.: Reasoning to attend: Try to understand how$$<$$ seg$$>$$ token works. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 24722\u201324731 (2025)","DOI":"10.1109\/CVPR52734.2025.02302"},{"key":"21_CR32","doi-asserted-by":"crossref","unstructured":"Ramesh, K., Kumar, G.K., Swapna, K., Datta, D., Rajest, S.S.: A review of medical image segmentation algorithms. EAI Endorsed Trans. Pervasive Health & Technology 7(27) (2021)","DOI":"10.4108\/eai.12-4-2021.169184"},{"key":"21_CR33","doi-asserted-by":"crossref","unstructured":"Rasheed, H., et al.: GlaMM: Pixel grounding large multimodal model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13009\u201313018 (2024)","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"21_CR34","doi-asserted-by":"crossref","unstructured":"Rasley, J., Rajbhandari, S., Ruwase, O., He, Y.: Deepspeed: System optimizations enable training deep learning models with over 100 billion parameters. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 3505\u20133506 (2020)","DOI":"10.1145\/3394486.3406703"},{"key":"21_CR35","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. Springer (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"7","key":"21_CR36","doi-asserted-by":"publisher","first-page":"1217","DOI":"10.1016\/j.media.2014.07.003","volume":"18","author":"RD Rudyanto","year":"2014","unstructured":"Rudyanto, R.D.: Comparing algorithms for automated vessel segmentation in computed tomography scans of the lung: the vessel12 study. Med. Image Anal. 18(7), 1217\u20131232 (2014)","journal-title":"Med. Image Anal."},{"key":"21_CR37","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102155","volume":"73","author":"A Saha","year":"2021","unstructured":"Saha, A., Hosseinzadeh, M., Huisman, H.: End-to-end prostate cancer detection in bpMRI via 3D CNNs: Effects of attention mechanisms, clinical priori and decoupled false positive reduction. Med. Image Anal. 73, 102155 (2021)","journal-title":"Med. Image Anal."},{"key":"21_CR38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.media.2017.06.015","volume":"42","author":"AAA Setio","year":"2017","unstructured":"Setio, A.A.A., et al.: Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: the luna16 challenge. Med. Image Anal. 42, 1\u201313 (2017)","journal-title":"Med. Image Anal."},{"key":"21_CR39","unstructured":"Singh, A., et\u00a0al.: Openai gpt-5 system card. arXiv preprint arXiv:2601.03267 (2025)"},{"key":"21_CR40","unstructured":"Team, G., et al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"21_CR41","doi-asserted-by":"crossref","unstructured":"Tong, Q., Lu, Z., Liu, J., Zheng, Y., Lu, Z.M.: MediSee: Reasoning-based pixel-level perception in medical images. In: Proceedings of the 33rd ACM International Conference on Multimedia, pp. 2742\u20132751 (2025)","DOI":"10.1145\/3746027.3754736"},{"key":"21_CR42","doi-asserted-by":"crossref","unstructured":"Wang, J., Ke, L.: LLM-Seg: Bridging image segmentation and large language model reasoning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1765\u20131774 (2024)","DOI":"10.1109\/CVPRW63382.2024.00183"},{"issue":"5","key":"21_CR43","doi-asserted-by":"publisher","first-page":"1243","DOI":"10.1049\/ipr2.12419","volume":"16","author":"R Wang","year":"2022","unstructured":"Wang, R., Lei, T., Cui, R., Zhang, B., Meng, H., Nandi, A.K.: Medical image segmentation using deep learning: a survey. IET Image Proc. 16(5), 1243\u20131267 (2022)","journal-title":"IET Image Proc."},{"key":"21_CR44","unstructured":"Wang, X., et al.: SegLLM: Multi-round reasoning segmentation. arXiv preprint arXiv:2410.18923 (2024)"},{"key":"21_CR45","doi-asserted-by":"publisher","first-page":"144591","DOI":"10.1109\/ACCESS.2019.2944958","volume":"7","author":"Y Wang","year":"2019","unstructured":"Wang, Y., Zhao, L., Wang, M., Song, Z.: Organ at risk segmentation in head and neck CT images using a two-stage segmentation framework based on 3D u-net. IEEE Access 7, 144591\u2013144602 (2019)","journal-title":"IEEE Access"},{"issue":"2","key":"21_CR46","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1162\/neco.1989.1.2.270","volume":"1","author":"RJ Williams","year":"1989","unstructured":"Williams, R.J., Zipser, D.: A learning algorithm for continually running fully recurrent neural networks. Neural Comput. 1(2), 270\u2013280 (1989)","journal-title":"Neural Comput."},{"key":"21_CR47","unstructured":"Xing, Y., et al.: MedVL-SAM2: A unified 3D Medical vision-language model for multimodal reasoning and prompt-driven segmentation. arXiv preprint arXiv:2601.09879 (2026)"},{"issue":"3","key":"21_CR48","doi-asserted-by":"publisher","first-page":"036501","DOI":"10.1117\/1.JMI.5.3.036501","volume":"5","author":"K Yan","year":"2018","unstructured":"Yan, K., Wang, X., Lu, L., Summers, R.M.: Deeplesion: automated mining of large-scale lesion annotations and universal lesion detection with deep learning. J. Med. Imaging 5(3), 036501\u2013036501 (2018)","journal-title":"J. Med. Imaging"},{"key":"21_CR49","unstructured":"Yan, Z., et al.: MedReasoner: Reinforcement learning drives reasoning grounding from clinical thought to pixel-level precision. arXiv preprint arXiv:2508.08177 (2025)"},{"key":"21_CR50","unstructured":"Yang, S., et al.: Lisa++: An improved baseline for reasoning segmentation with large language model. arXiv preprint arXiv:2312.17240 (2023)"},{"key":"21_CR51","unstructured":"Ye, J., et\u00a0al.: Sa-Med2D-20m dataset: Segment anything in 2d medical imaging with 20 million masks. arXiv preprint arXiv:2311.11969 (2023)"},{"key":"21_CR52","unstructured":"Zhang, A., Yao, Y., Ji, W., Liu, Z., Chua, T.S.: Next-chat: An LMM for chat, detection and segmentation. arXiv preprint arXiv:2311.04498 (2023)"},{"issue":"1","key":"21_CR53","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1038\/s41592-024-02499-w","volume":"22","author":"T Zhao","year":"2025","unstructured":"Zhao, T., et al.: A foundation model for joint segmentation, detection and recognition of biomedical objects across nine modalities. Nat. Methods 22(1), 166\u2013176 (2025)","journal-title":"Nat. Methods"},{"key":"21_CR54","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Rahman\u00a0Siddiquee, M.M., Tajbakhsh, N., Liang, J.: UNet++: A nested u-net architecture for medical image segmentation. In: International Workshop on Deep Learning in Medical Image Analysis, pp. 3\u201311. Springer (2018)","DOI":"10.1007\/978-3-030-00889-5_1"}],"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\/978-3-032-37196-6_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T09:35:38Z","timestamp":1789032938000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37196-6_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032371959","9783032371966"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37196-6_21","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":"11 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"}}]}}