{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T14:02:50Z","timestamp":1790258570048,"version":"4.1.0"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032381880","type":"print"},{"value":"9783032381897","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T00:00:00Z","timestamp":1790294400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T00:00:00Z","timestamp":1790294400000},"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":[[2027]]},"DOI":"10.1007\/978-3-032-38189-7_12","type":"book-chapter","created":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T13:31:45Z","timestamp":1790256705000},"page":"122-132","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CTTok: Voxel-Abulary for\u00a0Autoregressive 3D CT Volume Generation with\u00a0Large Language Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2005-0986","authenticated-orcid":false,"given":"Jiayi","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0261-2660","authenticated-orcid":false,"given":"Hadrien","family":"Reynaud","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1061-8990","authenticated-orcid":false,"given":"Mischa","family":"Dombrowski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7379-218X","authenticated-orcid":false,"given":"Xiaoliang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2932-3105","authenticated-orcid":false,"given":"Ibrahim Ethem","family":"Hamamci","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4435-7207","authenticated-orcid":false,"given":"Suprosanna","family":"Shit","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7266-9844","authenticated-orcid":false,"given":"Sezgin","family":"Er","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4136-5690","authenticated-orcid":false,"given":"Bjoern","family":"Menze","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7813-5023","authenticated-orcid":false,"given":"Bernhard","family":"Kainz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,25]]},"reference":[{"key":"12_CR1","unstructured":"Brooks, T., Peebles, B., Holmes, C., et\u00a0al.: Video generation models as world simulators. OpenAI Blog 1(8), 1 (2024). https:\/\/openai.com\/index\/video-generation-models-as-world-simulators\/"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Cao, H., Wang, Y., Chen, J.O.: Swin-unet: unet-like pure transformer for medical image segmentation. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds.) ECCV 2022 Workshops, pp. 205\u2013218. Springer, Cham (2023)","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Dombrowski, M., Zhang, W., Cechnicka, S.: Image generation diversity issues and how to tame them. In: CVPR 2025, pp. 3029\u20133039 (2025)","DOI":"10.1109\/CVPR52734.2025.00288"},{"key":"12_CR4","unstructured":"Dombrowski, M., Kainz, B.: Can diffusion models generalize? Privacy and fairness trade-offs for medical data sharing. In: MIDL 2025 (2025)"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Douze, M., Guzhva, A., Deng, C.: The faiss library. IEEE Trans. Big Data (2025)","DOI":"10.1109\/TBDATA.2025.3618474"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: CVPR 2021, pp. 12873\u201312883 (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Giuffr\u00e8, M., Shung, D.L.: Harnessing the power of synthetic data in healthcare: innovation, application, and privacy. NPJ Digit. Med. 6(1), 186 (2023)","DOI":"10.1038\/s41746-023-00927-3"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Guo, P., Zhao, C., Yang, D.: MAISI: medical ai for synthetic imaging. arXiv:2409.11169 (2025)","DOI":"10.1109\/WACV61041.2025.00435"},{"key":"12_CR9","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-025-01599-y","author":"IE Hamamci","year":"2026","unstructured":"Hamamci, I.E., Er, S., Wang, C., et al.: Generalist foundation models from a multimodal dataset for 3d computed tomography. Nat. Biomed. Eng. (2026). https:\/\/doi.org\/10.1038\/s41551-025-01599-y","journal-title":"Nat. Biomed. Eng."},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"He, J., Yu, Q., Liu, Q., Chen, L.C.: Flowtok: Flowing seamlessly across text and image tokens. arXiv:2503.10772 (2025)","DOI":"10.1109\/ICCV51701.2025.01544"},{"key":"12_CR11","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS 2020, vol. 33, pp. 6840\u20136851 (2020)"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Huang, N., Gokaslan, A., Kuleshov, V., Tompkin, J.: The GAN is dead; long live the GAN! a modern GAN baseline. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 37, pp. 44177\u201344215 (2024)","DOI":"10.52202\/079017-1402"},{"key":"12_CR13","unstructured":"Jolicoeur-Martineau, A.: The relativistic discriminator: a key element missing from standard GAN. In: ICLR 2019 (2019)"},{"key":"12_CR14","unstructured":"Jordan, K., Jin, Y., Boza, V., et\u00a0al.: Muon: An optimizer for hidden layers in neural networks (2024). https:\/\/kellerjordan.github.io\/posts\/muon\/"},{"key":"12_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrai.2025.100021","volume":"2","author":"JP Kao","year":"2025","unstructured":"Kao, J.P., Kao, H.T.: Large language models in radiology: a technical and clinical perspective. Eur. J. Radiol. Artif. Intell. 2, 100021 (2025)","journal-title":"Eur. J. Radiol. Artif. Intell."},{"key":"12_CR16","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv:1412.6980 (2014)"},{"issue":"4","key":"12_CR17","doi-asserted-by":"publisher","first-page":"1166","DOI":"10.1038\/s41591-024-02838-6","volume":"30","author":"I Ktena","year":"2024","unstructured":"Ktena, I., Wiles, O., Albuquerque, I., et al.: Generative models improve fairness of medical classifiers under distribution shifts. Nat. Med. 30(4), 1166\u20131173 (2024)","journal-title":"Nat. Med."},{"key":"12_CR18","unstructured":"Lipman, Y., Chen, R.T., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. In: ICLR 2023 (2022)"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"McIntosh-Smith, S., Alam, S.R., Woods, C.: Isambard-AI: a leadership class supercomputer optimised specifically for artificial intelligence. arXiv2410.11199 (2024)","DOI":"10.1145\/3725789.3725794"},{"key":"12_CR20","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1007\/978-3-031-18576-2_12","volume-title":"Deep Generative Models","author":"WHL Pinaya","year":"2022","unstructured":"Pinaya, W.H.L., Tudosiu, P.D., Dafflon, J., et al.: Brain imaging generation with latent diffusion models. In: Mukhopadhyay, A., Oksuz, I., Engelhardt, S., Zhu, D., Yuan, Y. (eds.) Deep Generative Models, pp. 117\u2013126. Springer, Cham (2022)"},{"issue":"5","key":"12_CR21","doi-asserted-by":"publisher","first-page":"2156","DOI":"10.1109\/TMI.2025.3650412","volume":"45","author":"S Rassmann","year":"2026","unstructured":"Rassmann, S., K\u00fcgler, D., Ewert, C., Reuter, M.: Regression is all you need for medical image translation. IEEE Trans. Med. Imaging 45(5), 2156\u20132172 (2026). https:\/\/doi.org\/10.1109\/TMI.2025.3650412","journal-title":"IEEE Trans. Med. Imaging"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR 2022, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"12_CR23","first-page":"234","volume-title":"MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015, pp. 234\u2013241. Springer, Cham (2015)"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"Skorokhodov, I., Tulyakov, S., Elhoseiny, M.: StyleGAN-V: a continuous video generator with the price, image quality and perks of StyleGAN2. arXiv:2112.14683 (2021)","DOI":"10.1109\/CVPR52688.2022.00361"},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Tudosiu, P.D., Pinaya, W.H.L., Graham, M.S.O.: Morphology-preserving autoregressive 3d generative modelling of the brain. In: Zhao, C., Svoboda, D., Wolterink, J.M., Escobar, M. (eds.) Simulation and Synthesis in Medical Imaging, pp. 66\u201378. Springer, Cham (2022)","DOI":"10.1007\/978-3-031-16980-9_7"},{"key":"12_CR26","unstructured":"Unterthiner, T., Van\u00a0Steenkiste, S., Kurach, K.o.: Towards accurate generative models of video: A new metric & challenges. arXiv:1812.01717 (2018)"},{"key":"12_CR27","unstructured":"VLM3D Organizers: VLM3D challenge: Vision-language modeling in 3D medical imaging (2025). https:\/\/vlm3dchallenge.com\/. ICCV 2025 Workshop"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Wang, J., Reynaud, H., Erick, F.X., Kainz, B.: CTFlow: Video-inspired latent flow matching for 3d ct synthesis. arXiv:2508.12900 (2025)","DOI":"10.1109\/ICCVW69036.2025.00703"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Wasserthal, J., Breit, H.C., Meyer, M.T., et\u00a0al.: Totalsegmentator: robust segmentation of 104 anatomic structures in CT images. Radiol. Artif. Intell. 5(5), e230024 (2023)","DOI":"10.1148\/ryai.230024"},{"issue":"8","key":"12_CR30","doi-asserted-by":"publisher","first-page":"2456","DOI":"10.1109\/TMI.2024.3415032","volume":"43","author":"Y Xu","year":"2024","unstructured":"Xu, Y., Sun, L., Peng, W., et al.: Medsyn: text-guided anatomy-aware synthesis of high-fidelity 3d CT images. IEEE Trans. Med. Imaging 43(8), 2456\u20132470 (2024). https:\/\/doi.org\/10.1109\/TMI.2024.3415032","journal-title":"IEEE Trans. Med. Imaging"},{"key":"12_CR31","unstructured":"Yang, A., Li, A., Yang, B., et\u00a0al.: Qwen3 technical report. arXiv:2505.09388 (2025)"},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"Yu, L., Lezama, J., Gundavarapu, N.B.: SPAE: semantic pyramid AutoEncoder for multimodal generation with frozen LLMs. In: NeurIPS, vol. 36, pp. 52692\u201352704 (2023)","DOI":"10.52202\/075280-2294"},{"key":"12_CR33","doi-asserted-by":"crossref","unstructured":"Yu, Q., He, J., Deng, X., Shen, X., Chen, L.C.: Randomized autoregressive visual generation. arXiv:2411.00776 (2024)","DOI":"10.1109\/ICCV51701.2025.01713"},{"key":"12_CR34","first-page":"128940","volume":"37","author":"Q Yu","year":"2024","unstructured":"Yu, Q., Weber, M., Deng, X., et al.: An image is worth 32 tokens for reconstruction and generation. NeurIPS 37, 128940\u2013128966 (2024)","journal-title":"NeurIPS"},{"key":"12_CR35","unstructured":"Yu, S., Tack, J., Mo, S., et\u00a0al.: Generating videos with dynamics-aware implicit generative adversarial networks. In: ICLR - arXiv:2202.10571 (2022)"},{"key":"12_CR36","doi-asserted-by":"crossref","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training. In: ICCV, pp. 11975\u201311986 (2023)","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"12_CR37","doi-asserted-by":"crossref","unstructured":"Zhao, C., Guo, P., Yang, D.: MAISI-v2: accelerated 3d high-resolution medical image synthesis with rectified flow and region-specific contrastive loss. arXiv:2508.05772 (2025)","DOI":"10.1609\/aaai.v40i15.38309"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-38189-7_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T13:32:05Z","timestamp":1790256725000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-38189-7_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,25]]},"ISBN":["9783032381880","9783032381897"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-38189-7_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,25]]},"assertion":[{"value":"25 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no relevant competing interests.","order":1,"name":"Ethics","label":"Disclosure of Interests","group":{"name":"EthicsHeading","label":"Ethics"}},{"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":"Strasbourg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","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":"27 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 October 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2026\/en\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}