{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T10:50:15Z","timestamp":1761130215612,"version":"3.44.0"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032051264","type":"print"},{"value":"9783032051271","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\/978-3-032-05127-1_9","type":"book-chapter","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T21:16:43Z","timestamp":1758316603000},"page":"88-97","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["BioD2C: A Dual-Level Semantic Consistency Constraint Framework for\u00a0Biomedical VQA"],"prefix":"10.1007","author":[{"given":"Zhengyang","family":"Ji","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shang","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Jia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yutao","family":"Yue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,20]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"Aberdam, A., et al.: Clipter: Looking at the bigger picture in scene text recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 21706\u201321717 (2023)","DOI":"10.1109\/ICCV51070.2023.01984"},{"key":"9_CR2","unstructured":"Achiam, J., et\u00a0al.: GPT-4 Technical Report (2023). arXiv preprint arXiv:2303.08774"},{"key":"9_CR3","unstructured":"Alayrac, J.B., et\u00a0al.: Flamingo: a visual language model for few-shot learning. Adv. Neural Inf. Process. Syst. pp. 23716\u201323736 (2022)"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Feng, J., Huang, D.: Optimal gradient checkpoint search for arbitrary computation graphs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11433\u201311442 (2021)","DOI":"10.1109\/CVPR46437.2021.01127"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Ganz, R., et al.: Question aware vision transformer for multimodal reasoning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13861\u201313871 (2024)","DOI":"10.1109\/CVPR52733.2024.01315"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"Ganz, R., Nuriel, O., Aberdam, A., Kittenplon, Y., Mazor, S., Litman, R.: Towards models that can see and read. In: 2023 IEEE\/CVF International Conference on Computer Vision, pp. 21661\u201321671 (2023)","DOI":"10.1109\/ICCV51070.2023.01985"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"9_CR8","doi-asserted-by":"crossref","unstructured":"He, X., Zhang, Y., Mou, L., Xing, E., Xie, P.: Pathvqa: 30000+ questions for medical visual question answering (2020). arXiv preprint arXiv:2003.10286","DOI":"10.36227\/techrxiv.13127537"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. pp. 1735\u20131780 (1997)","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"9_CR10","unstructured":"Hurst, A., et\u00a0al.: GPT-4o system card (2024). arXiv preprint arXiv:2410.21276"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Lau, J.J., Gayen, S., Ben\u00a0Abacha, A., Demner-Fushman, D.: A dataset of clinically generated visual questions and answers about radiology images. Sci. Data, pp. 1\u201310 (2018)","DOI":"10.1038\/sdata.2018.251"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Li, C., et al.: Llava-med: Training a large language-and-vision assistant for biomedicine in one day. Adv. Neural Inf. Process. Syst. pp. 28541\u201328564 (2023)","DOI":"10.32388\/VLXB6M"},{"key":"9_CR13","unstructured":"Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., Hoi, S.C.H.: Align before fuse: vision and language representation learning with momentum distillation. Adv. Neural Inf. Process. Syst. pp. 9694\u20139705 (2021)"},{"key":"9_CR14","unstructured":"Lin, C.Y.: Rouge: A package for automatic evaluation of summaries. In: Text summarization branches out, pp. 74\u201381 (2004)"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Lin, W., et al.: Pmc-clip: Contrastive language-image pre-training using biomedical documents. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 525\u2013536 (2023)","DOI":"10.1007\/978-3-031-43993-3_51"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Liu, B., Zhan, L.M., Xu, L., Ma, L., Yang, Y., Wu, X.M.: Slake: A semantically-labeled knowledge-enhanced dataset for medical visual question answering. In: IEEE International Symposium on Biomedical Imaging, pp. 1650\u20131654 (2021)","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"9_CR17","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2019)"},{"key":"9_CR18","unstructured":"Moor, M., et al.: Med-flamingo: a multimodal medical few-shot learner. In: Machine Learning for Health, pp. 353\u2013367 (2023)"},{"key":"9_CR19","unstructured":"Mullappilly, S.S., et\u00a0al.: Bimedix2: Bio-medical expert LMM for diverse medical modalities (2024). arXiv preprint arXiv:2412.07769"},{"key":"9_CR20","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":"9_CR21","doi-asserted-by":"crossref","unstructured":"Roberts, R.J.: Pubmed central: The genbank of the published literature. National Academy Sci. pp. 381\u2013382 (2001)","DOI":"10.1073\/pnas.98.2.381"},{"key":"9_CR22","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. Adv. Neural Inf. Process. Syst. pp. 1735\u20131780 (2014)"},{"key":"9_CR23","doi-asserted-by":"crossref","unstructured":"Wu, C., Lin, W., Zhang, X., Zhang, Y., Xie, W., Wang, Y.: Pmc-llama: toward building open-source language models for medicine. Journal of the American Medical Informatics Association, pp. 1833\u20131843 (2024)","DOI":"10.1093\/jamia\/ocae045"},{"key":"9_CR24","unstructured":"Wu, C., Zhang, X., Zhang, Y., Wang, Y., Xie, W.: Towards generalist foundation model for radiology by leveraging web-scale 2D AND 3D medical data (2023). arXiv preprint arXiv:2308.02463"},{"key":"9_CR25","unstructured":"Zhang, K., et\u00a0al.: A generalist vision\u2013language foundation model for diverse biomedical tasks. Nat. Med. pp. 1\u201313 (2024)"},{"key":"9_CR26","unstructured":"Zhang, X., et al.: Pmc-vqa: Visual instruction tuning for medical visual question answering (2023). arXiv preprint arXiv:2305.10415"}],"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\/978-3-032-05127-1_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T21:16:50Z","timestamp":1758316610000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-05127-1_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,20]]},"ISBN":["9783032051264","9783032051271"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-05127-1_9","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 to declare that are relevant to the content of this article.","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"}}]}}