{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,22]],"date-time":"2026-02-22T07:00:37Z","timestamp":1771743637577,"version":"3.50.1"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032049704","type":"print"},{"value":"9783032049711","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\/978-3-032-04971-1_1","type":"book-chapter","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T17:09:56Z","timestamp":1758301796000},"page":"3-12","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["$${\\mu }^2$$ Tokenizer: Differentiable Multi-Scale Multi-Modal Tokenizer for\u00a0Radiology Report Generation"],"prefix":"10.1007","author":[{"given":"Siyou","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengyao","family":"Qin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huanan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Nie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arun J.","family":"Thirunavukarasu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juntao","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Le","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,20]]},"reference":[{"key":"1_CR1","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 (2024)"},{"key":"1_CR2","unstructured":"Banerjee, S., Lavie, A.: METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In: Goldstein, J., Lavie, A., Lin, C.Y., Voss, C. (eds.) Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization. pp. 65\u201372. Association for Computational Linguistics, Ann Arbor, Michigan (2005)"},{"key":"1_CR3","unstructured":"Bassi, P.R., et al.: Radgpt: Constructing 3d image-text tumor datasets. arXiv preprint arXiv:2501.04678 (2025)"},{"key":"1_CR4","unstructured":"Everlight: Radiology unlocked: The global radiologist report 2025"},{"key":"1_CR5","unstructured":"Gao, L., Zhong, Y., Zeng, Y., Tan, H., Li, D., Zhao, Z.: Linvt: Empower your image-level large language model to understand videos. arXiv preprint arXiv:2412.05185 (2024)"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Hamamci, I.E., et al.: Developing generalist foundation models from a multimodal dataset for 3d computed tomography (2024)","DOI":"10.21203\/rs.3.rs-5271327\/v1"},{"key":"1_CR7","unstructured":"Hamamci, I.E., et\u00a0al.: A foundation model utilizing chest ct volumes and radiology reports for supervised-level zero-shot detection of abnormalities. arXiv preprint arXiv:2403.17834 (2024)"},{"key":"1_CR8","unstructured":"Jaegle, A., Gimeno, F., Brock, A., Vinyals, O., Zisserman, A., Carreira, J.: Perceiver: General perception with iterative attention. In: International Conference on Machine Learning, pp. 4651\u20134664. PMLR (2021)"},{"key":"1_CR9","first-page":"36722","volume":"35","author":"Y Ji","year":"2022","unstructured":"Ji, Y., et al.: Amos: A large-scale abdominal multi-organ benchmark for versatile medical image segmentation. Adv. Neural. Inf. Process. Syst. 35, 36722\u201336732 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1_CR10","unstructured":"Lin, C.Y.: ROUGE: A package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381. Association for Computational Linguistics, Barcelona, Spain (2004)"},{"key":"1_CR11","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning (2023)"},{"key":"1_CR12","doi-asserted-by":"publisher","unstructured":"Ostmeier, S., et al.: GREEN: Generative radiology report evaluation and error notation. In: Al-Onaizan, Y., Bansal, M., Chen, Y.N. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2024, pp. 374\u2013390. Association for Computational Linguistics, Miami, Florida, USA (2024). https:\/\/doi.org\/10.18653\/v1\/2024.findings-emnlp.21","DOI":"10.18653\/v1\/2024.findings-emnlp.21"},{"key":"1_CR13","doi-asserted-by":"publisher","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Isabelle, P., Charniak, E., Lin, D. (eds.) Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318. Association for Computational Linguistics, Philadelphia, Pennsylvania, USA (2002). https:\/\/doi.org\/10.3115\/1073083.1073135","DOI":"10.3115\/1073083.1073135"},{"key":"1_CR14","unstructured":"Rafailov, R., Sharma, A., Mitchell, E., Manning, C.D., Ermon, S., Finn, C.: Direct preference optimization: Your language model is secretly a reward model. In: Thirty-seventh Conference on Neural Information Processing Systems (2023)"},{"key":"1_CR15","doi-asserted-by":"publisher","unstructured":"Rosenkrantz, A.B.: Differences in perceptions among radiologists, referring physicians, and patients regarding language for incidental findings reporting 208(1), 140\u2013143. https:\/\/doi.org\/10.2214\/AJR.16.16633, publisher: American Roentgen Ray Society","DOI":"10.2214\/AJR.16.16633"},{"key":"1_CR16","doi-asserted-by":"crossref","unstructured":"Shaw, P., Uszkoreit, J., Vaswani, A.: Self-attention with relative position representations (2018)","DOI":"10.18653\/v1\/N18-2074"},{"key":"1_CR17","doi-asserted-by":"publisher","unstructured":"Thirunavukarasu, A.J., Ting, D.S.J., Elangovan, K., Gutierrez, L., Tan, T.F., Ting, D.S.W.: Large language models in medicine 29, 1930\u20131940. https:\/\/doi.org\/10.1038\/s41591-023-02448-8","DOI":"10.1038\/s41591-023-02448-8"},{"key":"1_CR18","unstructured":"Touvron, H., et al.: Llama: Open and efficient foundation language models (2023)"},{"key":"1_CR19","unstructured":"Wu, C., Zhang, X., Zhang, Y., Wang, Y., Xie, W.: Towards generalist foundation model for radiology (2023)"},{"key":"1_CR20","unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K.Q., Artzi, Y.: Bertscore: Evaluating text generation with BERT. CoRR abs\/1904.09675 (2019)"},{"key":"1_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2023.102714","volume":"146","author":"G Zhao","year":"2023","unstructured":"Zhao, G., Zhao, Z., Gong, W., Li, F.: Radiology report generation with medical knowledge and multilevel image-report alignment: a new method and its verification. Artif. Intell. Med. 146, 102714 (2023)","journal-title":"Artif. Intell. Med."}],"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\/978-3-032-04971-1_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,22]],"date-time":"2026-02-22T06:44:41Z","timestamp":1771742681000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04971-1_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,20]]},"ISBN":["9783032049704","9783032049711"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04971-1_1","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 in the paper","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"}}]}}