{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T07:42:48Z","timestamp":1758267768544,"version":"3.44.0"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032049773","type":"print"},{"value":"9783032049780","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T00:00:00Z","timestamp":1758240000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T00:00:00Z","timestamp":1758240000000},"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\/978-3-032-04978-0_23","type":"book-chapter","created":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T16:16:36Z","timestamp":1758212196000},"page":"237-246","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploring the\u00a0Design Space of\u00a03D MLLMs for\u00a0CT Report Generation"],"prefix":"10.1007","author":[{"given":"Mohammed","family":"Baharoon","sequence":"first","affiliation":[]},{"given":"Jun","family":"Ma","sequence":"additional","affiliation":[]},{"given":"Congyu","family":"Fang","sequence":"additional","affiliation":[]},{"given":"Augustin","family":"Toma","sequence":"additional","affiliation":[]},{"given":"Bo","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,19]]},"reference":[{"key":"23_CR1","unstructured":"Abdin, M., Aneja, J., Awadalla, H., Awadallah, A., Awan, A.A., et\u00a0al.: Phi-3 technical report: a highly capable language model locally on your phone. arXiv:2404.14219 (2024)"},{"key":"23_CR2","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:2404.00578 (2024)"},{"key":"23_CR3","unstructured":"Bannur, S., et al.: Maira-2: grounded radiology report generation. arXiv:2406.04449 (2024)"},{"key":"23_CR4","doi-asserted-by":"crossref","unstructured":"Bruls, R.J.M., Kwee, R.M.: Workload for radiologists during on-call hours: dramatic increase in the past 15 years. Insights Into Imaging 11(1), (2020)","DOI":"10.1186\/s13244-020-00925-z"},{"key":"23_CR5","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"23_CR6","unstructured":"Dubey, A., et al.: The llama 3 herd of models. arXiv:2407.21783 (2024)"},{"issue":"7345","key":"23_CR7","doi-asserted-by":"publisher","first-page":"1077","DOI":"10.1136\/bmj.324.7345.1077","volume":"324","author":"CJ Garvey","year":"2002","unstructured":"Garvey, C.J.: Computed tomography in clinical practice. BMJ 324(7345), 1077\u20131080 (2002)","journal-title":"BMJ"},{"key":"23_CR8","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. arXiv:2106.09685 (2021)"},{"key":"23_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":"23_CR10","unstructured":"Jiang, A.Q., et al.: Mistral 7b. arXiv preprint arXiv:2310.06825 (2023)"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Lavie, A., Agarwal, A.: Meteor: an automatic metric for mt evaluation with high levels of correlation with human judgments. In: Proceedings of the Second Workshop on Statistical Machine Translation, StatMT 2007, pp. 228\u2013231, USA, ACL (2007)","DOI":"10.3115\/1626355.1626389"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Lee, S., Youn, J., Kim, H., Kim, M., Yoon, S.H.: Cxr-llava: a multimodal large language model for interpreting chest x-ray images. Eur. Radiol. January 2025","DOI":"10.1007\/s00330-024-11339-6"},{"key":"23_CR13","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":"23_CR14","doi-asserted-by":"crossref","unstructured":"Li, W., et al.: Tokenpacker: efficient visual projector for multimodal llm. arXiv:2407.02392 (2024)","DOI":"10.1007\/s11263-025-02491-7"},{"key":"23_CR15","unstructured":"Lin, C.-Y.: ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381, Barcelona, Spain, ACL, July 2004"},{"key":"23_CR16","unstructured":"Liu, C., et al.: Benchmarking and boosting radiology report generation for 3d high-resolution medical images. arXiv preprint arXiv:2406.07146 (2024)"},{"key":"23_CR17","unstructured":"Liu, H., Li, C., Li, Y., Li, B., Zhang, Y., Shen, S., Lee, Y.J.: Improved reasoning, ocr, and world knowledge, Llava-next (2024)"},{"key":"23_CR18","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems (2023)"},{"key":"23_CR19","unstructured":"Liu, S.-Y., et al.: Dora: weight-decomposed low-rank adaptation. arXiv:2402.09353 (2024)"},{"key":"23_CR20","first-page":"374","volume":"2024","author":"S Ostmeier","year":"2024","unstructured":"Ostmeier, S., et al.: Green: generative radiology report evaluation and error notation. Find. Assoc. Comput. Linguist. EMNLP 2024, 374\u2013390 (2024)","journal-title":"Find. Assoc. Comput. Linguist. EMNLP"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, ACL 2002, pp. 311\u2013318. USA, ACL (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"23_CR22","unstructured":"Team, G., et al.: Gemma 2: improving open language models at a practical size. arXiv:2408.00118 (2024)"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Troupis, C.J., Knight, R.A.H., Lau, K.K.P., et al.: What is the appropriate measure of radiology workload: study or image numbers? J. Med. Imaging Radiat. Oncol. 68(5), 530\u2013539 (2024)","DOI":"10.1111\/1754-9485.13713"},{"key":"23_CR24","doi-asserted-by":"crossref","unstructured":"Wasserthal, J., et al.: Totalsegmentator: robust segmentation of 104 anatomic structures in ct images. Radiol. Artif. Intell. 5(5), (2023)","DOI":"10.1148\/ryai.230024"},{"key":"23_CR25","unstructured":"Wolf, T.: Huggingface\u2019s transformers: state-of-the-art natural language processing. arXiv:1910.03771 (2019)"},{"key":"23_CR26","doi-asserted-by":"crossref","unstructured":"Wu, C., Zhang, X., Zhang, Y., Wang, Y., Xie, W.: Medklip: medical knowledge enhanced language-image pre-training in radiology. arXiv:2301.02228 (2023)","DOI":"10.1101\/2023.01.10.23284412"},{"key":"23_CR27","unstructured":"Wu, C., Zhang, X., Zhang, Y., Wang, Y., Xie, W.: Towards generalist foundation model for radiology by leveraging web-scale 2d &3d medical data. arXiv preprint arXiv:2308.02463 (2023)"},{"key":"23_CR28","unstructured":"Yang, A., et al.: Qwen2. 5 technical report. arXiv:2412.15115 (2024)"},{"key":"23_CR29","doi-asserted-by":"crossref","unstructured":"Zhao, W., Wu, C., Zhang, X., Zhang, Y., Wang, Y., Xie, W.: Ratescore: a metric for radiology report generation. arXiv:2406.16845 (2024)","DOI":"10.1101\/2024.06.24.24309405"},{"key":"23_CR30","unstructured":"Zhou, H.Y., Adithan, S., Acosta, J.N., Topol, E.J., Rajpurkar, P.: A generalist learner for multifaceted medical image interpretation. arXiv preprint arXiv:2405.07988 (2024)"}],"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\/978-3-032-04978-0_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T22:05:44Z","timestamp":1758233144000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04978-0_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,19]]},"ISBN":["9783032049773","9783032049780"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04978-0_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,19]]},"assertion":[{"value":"19 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors declare no competing interests.","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"}}]}}