{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T14:02:10Z","timestamp":1781272930177,"version":"3.54.1"},"publisher-location":"Cham","reference-count":21,"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_26","type":"book-chapter","created":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T16:17:16Z","timestamp":1758212236000},"page":"268-277","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["From Slices to\u00a0Volumes: Multi-scale Fusion of\u00a02D and\u00a03D Features for\u00a0CT Scan Report Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2967-3033","authenticated-orcid":false,"given":"Abdullah","family":"Hosseini","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9217-4173","authenticated-orcid":false,"given":"Ahmed","family":"Ibrahim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4145-5509","authenticated-orcid":false,"given":"Ahmed","family":"Serag","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,19]]},"reference":[{"key":"26_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. arXiv preprint arXiv:2404.00578 (2024)"},{"key":"26_CR2","unstructured":"Banerjee, S., Lavie, A.: Meteor: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization, pp. 65\u201372 (2005)"},{"key":"26_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102680","volume":"84","author":"P Bilic","year":"2023","unstructured":"Bilic, P., et al.: The liver tumor segmentation benchmark (LITS). Med. Image Anal. 84, 102680 (2023)","journal-title":"Med. Image Anal."},{"key":"26_CR4","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"26_CR5","unstructured":"Chen, H., et al.: 3D-CT-GPT: generating 3D radiology reports through integration of large vision-language models. arXiv preprint arXiv:2409.19330 (2024)"},{"key":"26_CR6","unstructured":"DeepSeek-AI, D.G., et al.: Deepseek-r1: incentivizing reasoning capability in LLMs via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)"},{"key":"26_CR7","doi-asserted-by":"crossref","unstructured":"Di\u00a0Piazza, T.: CT-AGRG: automated abnormality-guided report generation from 3D chest CT volumes. arXiv preprint arXiv:2408.11965 (2024)","DOI":"10.1109\/ISBI60581.2025.10981073"},{"key":"26_CR8","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"26_CR9","unstructured":"Dubey, A., et al.: The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)"},{"key":"26_CR10","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":"26_CR11","doi-asserted-by":"crossref","unstructured":"Hamamci, I.E., Er, S., Menze, B.: CT2Rep: automated radiology report generation for 3d medical imaging. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 476\u2013486. Springer (2024)","DOI":"10.1007\/978-3-031-72390-2_45"},{"key":"26_CR12","unstructured":"Lai, H., et al.: E3D-GPT: enhanced 3D visual foundation for medical vision-language model. arXiv preprint arXiv:2410.14200 (2024)"},{"key":"26_CR13","unstructured":"Lee, C., et al.: Read like a radiologist: efficient vision-language model for 3D medical imaging interpretation. arXiv preprint arXiv:2412.13558 (2024)"},{"key":"26_CR14","unstructured":"Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"26_CR15","doi-asserted-by":"crossref","unstructured":"Oh\u00a0Song, H., Xiang, Y., Jegelka, S., Savarese, S.: Deep metric learning via lifted structured feature embedding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4004\u20134012 (2016)","DOI":"10.1109\/CVPR.2016.434"},{"key":"26_CR16","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 of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"26_CR17","unstructured":"Saab, K., et al.: Capabilities of gemini models in medicine. arXiv preprint arXiv:2404.18416 (2024)"},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"Tang, Y., Yuan, Y., Tao, F., Tang, M.: Cross-modal augmented transformer for automated medical report generation. IEEE J. Transl. Eng. Health Med. (2025)","DOI":"10.1109\/JTEHM.2025.3536441"},{"issue":"8","key":"26_CR19","doi-asserted-by":"publisher","first-page":"1885","DOI":"10.1109\/TMI.2019.2894854","volume":"38","author":"X Xu","year":"2019","unstructured":"Xu, X., Zhou, F., Liu, B., Fu, D., Bai, X.: Efficient multiple organ localization in CT image using 3D region proposal network. IEEE Trans. Med. Imaging 38(8), 1885\u20131898 (2019)","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"1","key":"26_CR20","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1038\/s41597-022-01721-8","volume":"10","author":"J Yang","year":"2023","unstructured":"Yang, J., et al.: Medmnist v2-a large-scale lightweight benchmark for 2D and 3D biomedical image classification. Sci. Data 10(1), 41 (2023)","journal-title":"Sci. Data"},{"key":"26_CR21","unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K.Q., Artzi, Y.: Bertscore: evaluating text generation with bert. arXiv preprint arXiv:1904.09675 (2019)"}],"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_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T22:06:42Z","timestamp":1758233202000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04978-0_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,19]]},"ISBN":["9783032049773","9783032049780"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04978-0_26","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 that they have no known competing financial interests\u00a0or personal relationships that could have appeared to influence\u00a0the work reported in this 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"}}]}}