{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T09:10:44Z","timestamp":1758359444454,"version":"3.44.0"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032049834"},{"type":"electronic","value":"9783032049841"}],"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\/978-3-032-04984-1_40","type":"book-chapter","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T16:25:38Z","timestamp":1758299138000},"page":"415-425","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["R1Seg-3D: Rethinking Reasoning Segmentation for Medical 3D CTs"],"prefix":"10.1007","author":[{"given":"Qin","family":"Hao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Long","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengwei","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xujiong","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,20]]},"reference":[{"key":"40_CR1","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1016\/j.media.2019.04.002","volume":"56","author":"JJ Cerrolaza","year":"2019","unstructured":"Cerrolaza, J.J., et al.: Computational anatomy for multi-organ ANALYSIS IN MEDICAL IMAGING: A review. Med. Image Anal. 56, 44\u201367 (2019)","journal-title":"Med. Image Anal."},{"key":"40_CR2","doi-asserted-by":"crossref","unstructured":"\u00c7i\u00e7ek, \u00d6., Abdulkadir, A., Lienkamp, S.S., Brox, T., Ronneberger, O.: 3D U-net: learning dense volumetric segmentation from sparse annotation. In: Lecture Notes in Computer Science, pp. 424\u2013432 (2016)","DOI":"10.1007\/978-3-319-46723-8_49"},{"issue":"2","key":"40_CR3","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.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":"40_CR4","unstructured":"Chen, J., et al.: Transunet: Transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:210204306 (2021)"},{"key":"40_CR5","doi-asserted-by":"crossref","unstructured":"Hatamizadeh, A., et al.: UNETR: transformers for 3D medical image segmentation. In: Proceedings of the 2022 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 1748\u20131758. IEEE, Waikoloa (2022)","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"40_CR6","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. In: Proceedings of the 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3992\u20134003. IEEE (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"40_CR7","unstructured":"Oquab, M., et al.: Dinov2: learning robust visual features without supervision. arXiv preprint arXiv:230407193, (2024)"},{"issue":"1","key":"40_CR8","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":"40_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103370","volume":"99","author":"W Lei","year":"2025","unstructured":"Lei, W., Xu, W., Li, K., Zhang, X., Zhang, S.: MedLSAM: localize and segment anything model for 3D CT images. Med. Image Anal. 99, 103370 (2025)","journal-title":"Med. Image Anal."},{"key":"40_CR10","unstructured":"AI@Meta: Llama 3 Model Card (2024)"},{"key":"40_CR11","unstructured":"Qwen Team: Qwen2.5: A party of foundation models (2024)"},{"issue":"3","key":"40_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3641289","volume":"15","author":"Y Chang","year":"2024","unstructured":"Chang, Y., et al.: A survey on evaluation of large language models. ACM Trans. Intell. Syst. Technol. 15(3), 1\u201345 (2024)","journal-title":"ACM Trans. Intell. Syst. Technol."},{"issue":"8","key":"40_CR13","doi-asserted-by":"publisher","first-page":"5625","DOI":"10.1109\/TPAMI.2024.3369699","volume":"46","author":"J Zhang","year":"2024","unstructured":"Zhang, J., Huang, J., Jin, S., Lu, S.: Vision-language models for vision tasks: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 46(8), 5625\u20135644 (2024)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"40_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. Adv. Neural. Inf. Process. Syst. 36, 28541\u201328564 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"40_CR15","doi-asserted-by":"crossref","unstructured":"Luo, Y., et al.: BioMedGPT: an open multimodal large language model for bioMedicine. IEEE J. Biomed. Health Inf. 1\u201312 (2024)","DOI":"10.1109\/JBHI.2024.3505955"},{"key":"40_CR16","doi-asserted-by":"crossref","unstructured":"Lai, X., et al.: LISA: reasoning segmentation via large language model. In: Proceedings of the 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9579\u20139589. IEEE, Seattle (2024)","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"40_CR17","doi-asserted-by":"crossref","unstructured":"Ren, Z., et al.: PixelLM: pixel reasoning with large multimodal model. In: Proceedings of the 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 26364\u201326373. IEEE, Seattle (2024)","DOI":"10.1109\/CVPR52733.2024.02491"},{"key":"40_CR18","unstructured":"Yang, S., Qu, T., Lai, X., Tian, Z., Peng, B., Liu, S., Jia, J.: LISA++: an improved baseline for reasoning segmentation with large language Model. arXiv preprint arXiv:231217240 (2024)"},{"key":"40_CR19","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Ma, Y., Zhang, E., Bai, X.: PSALM: pixelwise segmentation with large multi-modal model. In: Proceedings of the Lecture Notes in Computer Science, pp. 74\u201391. Springer, Cham (2024)","DOI":"10.1007\/978-3-031-72754-2_5"},{"key":"40_CR20","doi-asserted-by":"crossref","unstructured":"Yuan, Y., et al.: Osprey: Pixel understanding with visual instruction tuning. In: Proceedings of the 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 28202\u201328211. IEEE, Seattle (2024)","DOI":"10.1109\/CVPR52733.2024.02664"},{"key":"40_CR21","first-page":"71737","volume":"37","author":"T Zhang","year":"2025","unstructured":"Zhang, T., et al.: Omg-llava: bridging image-level, object-level, pixel-level reasoning and understanding. Adv. Neural. Inf. Process. Syst. 37, 71737\u201371767 (2025)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"40_CR22","doi-asserted-by":"crossref","unstructured":"Rasheed, H., et al.: GLaMM: pixel grounding large multimodal model. In: Proceedings of the 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13009\u201313018. IEEE, Seattle (2024)","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"40_CR23","unstructured":"Bai, F., Du, Y., Huang, T., Meng, M.Q.-H., Zhao, B.: M3D: Advancing 3d medical image analysis with multi-modal large language models. arXiv preprint arXiv:240400578, (2024)"},{"key":"40_CR24","doi-asserted-by":"crossref","unstructured":"Chen, Y.-C., Li, W.-H., Sun, C., Wang, Y.-C.F., Chen, C.-S.: SAM4MLLM: enhance multi-modal large language model for referring expression segmentation. In: Lecture Notes in Computer Science, pp. 323\u2013340 (2024)","DOI":"10.1007\/978-3-031-73004-7_19"},{"key":"40_CR25","doi-asserted-by":"crossref","unstructured":"Wysocza\u0144ska, M., Sim\u00e9oni, O., Ramamonjisoa, M., Bursuc, A., Trzci\u0144ski, T., P\u00e9rez, P.: CLIP-DINOiser: teaching CLIP a few DINO tricks for open-vocabulary semantic segmentation. In: Lecture Notes in Computer Science, pp. 320\u2013337 (2024)","DOI":"10.1007\/978-3-031-73030-6_18"},{"key":"40_CR26","doi-asserted-by":"crossref","unstructured":"Dong, X., et al.: MaskCLIP: masked self-distillation advances contrastive language-image pretraining. In: Proceedings of the 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10995\u201311005. IEEE, Vancouver (2023)","DOI":"10.1109\/CVPR52729.2023.01058"},{"issue":"6","key":"40_CR27","doi-asserted-by":"publisher","first-page":"1013","DOI":"10.1007\/s11548-024-03083-5","volume":"19","author":"B Cui","year":"2024","unstructured":"Cui, B., Islam, M., Bai, L., Ren, H.: Surgical-DINO: adapter learning of foundation models for depth estimation in endoscopic surgery. Int. J. Comput. Assist. Radiol. Surg. 19(6), 1013\u20131020 (2024)","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"issue":"1","key":"40_CR28","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1038\/s42256-024-00965-w","volume":"7","author":"F P\u00e9rez-Garc\u00eda","year":"2025","unstructured":"P\u00e9rez-Garc\u00eda, F., et al.: Exploring scalable medical image encoders beyond text supervision. Nat. Mach. Intell. 7(1), 119\u2013130 (2025)","journal-title":"Nat. Mach. Intell."},{"key":"40_CR29","first-page":"110746","volume":"37","author":"Y Du","year":"2025","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 (2025)","journal-title":"Adv. Neural. Inf. Process. Syst."}],"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\/978-3-032-04984-1_40","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T16:25:48Z","timestamp":1758299148000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04984-1_40"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,20]]},"ISBN":["9783032049834","9783032049841"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04984-1_40","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"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":"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"}}]}}