{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T15:34:31Z","timestamp":1776440071234,"version":"3.51.2"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032049803","type":"print"},{"value":"9783032049810","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\/978-3-032-04981-0_20","type":"book-chapter","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T05:10:05Z","timestamp":1758258605000},"page":"205-215","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["DualPrompt-MedCap: A Dual-Prompt Enhanced Approach for\u00a0Medical Image Captioning"],"prefix":"10.1007","author":[{"given":"Yining","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mukesh","family":"Prasad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ali","family":"Braytee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,20]]},"reference":[{"key":"20_CR1","doi-asserted-by":"crossref","unstructured":"Bodenreider, O.: The unified medical language system (umls): integrating biomedical terminology. Nucleic acids research 32(suppl_1), D267\u2013D270 (2004)","DOI":"10.1093\/nar\/gkh061"},{"key":"20_CR2","doi-asserted-by":"crossref","unstructured":"Chen, Z., Song, Y., Chang, T.H., Wan, X.: Generating radiology reports via memory-driven transformer. arXiv preprint arXiv:2010.16056 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"20_CR3","doi-asserted-by":"crossref","unstructured":"Farahani, N., Parwani, A.V., Pantanowitz, L.: Whole slide imaging in pathology: advantages, limitations, and emerging perspectives. Pathology and Laboratory Medicine International pp. 23\u201333 (2015)","DOI":"10.2147\/PLMI.S59826"},{"issue":"1","key":"20_CR4","first-page":"1","volume":"3","author":"Y Gu","year":"2021","unstructured":"Gu, Y., Tinn, R., Cheng, H., Lucas, M., Usuyama, N., Liu, X., Naumann, T., Gao, J., Poon, H.: Domain-specific language model pretraining for biomedical natural language processing. ACM Transactions on Computing for Healthcare (HEALTH) 3(1), 1\u201323 (2021)","journal-title":"ACM Transactions on Computing for Healthcare (HEALTH)"},{"key":"20_CR5","unstructured":"Huang, X., Zhang, Y., Ma, J., Tian, W., Feng, R., Zhang, Y., Li, Y., Guo, Y., Zhang, L.: Tag2text: Guiding vision-language model via image tagging. arXiv preprint arXiv:2303.05657 (2023)"},{"key":"20_CR6","doi-asserted-by":"crossref","unstructured":"Irvin, J., Rajpurkar, P., Ko, M., Yu, Y., Ciurea-Ilcus, S., Chute, C., Marklund, H., Haghgoo, B., Ball, R., Shpanskaya, K., et\u00a0al.: Chexpert: A large chest radiograph dataset with uncertainty labels and expert comparison. In: Proceedings of the AAAI conference on artificial intelligence. vol.\u00a033, pp. 590\u2013597 (2019)","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"20_CR7","unstructured":"Jain, S., Agrawal, A., Saporta, A., Truong, S.Q., Duong, D.N., Bui, T., Chambon, P., Zhang, Y., Lungren, M.P., Ng, A.Y., et\u00a0al.: Radgraph: Extracting clinical entities and relations from radiology reports. arXiv preprint arXiv:2106.14463 (2021)"},{"key":"20_CR8","unstructured":"Jing, B., Xie, P., Xing, E.: On the automatic generation of medical imaging reports. arXiv preprint arXiv:1711.08195 (2017)"},{"issue":"1","key":"20_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2018.251","volume":"5","author":"JJ Lau","year":"2018","unstructured":"Lau, J.J., Gayen, S., Ben Abacha, A., Demner-Fushman, D.: A dataset of clinically generated visual questions and answers about radiology images. Scientific data 5(1), 1\u201310 (2018)","journal-title":"Scientific data"},{"key":"20_CR10","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In: International conference on machine learning. pp. 19730\u201319742. PMLR (2023)"},{"key":"20_CR11","unstructured":"Li, Y., Liang, X., Hu, Z., Xing, E.P.: Hybrid retrieval-generation reinforced agent for medical image report generation. Advances in neural information processing systems 31 (2018)"},{"key":"20_CR12","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: 2021 IEEE 18th international symposium on biomedical imaging (ISBI). pp. 1650\u20131654. IEEE (2021)","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"20_CR13","unstructured":"Liu, G., Hsu, T., McDermott, M., Boag, W., Weng, W., Szolovits, P., Ghassemi, M.: Clinically accurate chest x-ray report generation. corr. arXiv preprint arXiv:1904.02633 (2019)"},{"issue":"6","key":"20_CR14","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1038\/s41551-020-00682-w","volume":"5","author":"MY Lu","year":"2021","unstructured":"Lu, M.Y., Williamson, D.F., Chen, T.Y., Chen, R.J., Barbieri, M., Mahmood, F.: Data-efficient and weakly supervised computational pathology on whole-slide images. Nature biomedical engineering 5(6), 555\u2013570 (2021)","journal-title":"Nature biomedical engineering"},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"Neumann, M., King, D., Beltagy, I., Ammar, W.: Scispacy: fast and robust models for biomedical natural language processing. arXiv preprint arXiv:1902.07669 (2019)","DOI":"10.18653\/v1\/W19-5034"},{"issue":"5","key":"20_CR16","doi-asserted-by":"publisher","first-page":"e253","DOI":"10.1016\/S1470-2045(19)30154-8","volume":"20","author":"MKK Niazi","year":"2019","unstructured":"Niazi, M.K.K., Parwani, A.V., Gurcan, M.N.: Digital pathology and artificial intelligence. Lancet Oncol. 20(5), e253\u2013e261 (2019)","journal-title":"Lancet Oncol."},{"key":"20_CR17","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":"20_CR18","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International conference on machine learning. pp. 8748\u20138763. PmLR (2021)"},{"issue":"4","key":"20_CR19","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1162\/coli.2009.35.4.35405","volume":"35","author":"E Reiter","year":"2009","unstructured":"Reiter, E., Belz, A.: An investigation into the validity of some metrics for automatically evaluating natural language generation systems. Comput. Linguist. 35(4), 529\u2013558 (2009)","journal-title":"Comput. Linguist."},{"key":"20_CR20","first-page":"596","volume":"33","author":"K Sohn","year":"2020","unstructured":"Sohn, K., Berthelot, D., Carlini, N., Zhang, Z., Zhang, H., Raffel, C.A., Cubuk, E.D., Kurakin, A., Li, C.L.: Fixmatch: Simplifying semi-supervised learning with consistency and confidence. Adv. Neural. Inf. Process. Syst. 33, 596\u2013608 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"20_CR21","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: A neural image caption generator. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"20_CR22","doi-asserted-by":"crossref","unstructured":"Wang, X., Peng, Y., Lu, L., Lu, Z., Summers, R.M.: Tienet: Text-image embedding network for common thorax disease classification and reporting in chest x-rays. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 9049\u20139058 (2018)","DOI":"10.1109\/CVPR.2018.00943"},{"key":"20_CR23","unstructured":"Xue, L., Shu, M., Awadalla, A., Wang, J., Yan, A., Purushwalkam, S., Zhou, H., Prabhu, V., Dai, Y., Ryoo, M.S., et\u00a0al.: xgen-mm (blip-3): A family of open large multimodal models. arXiv preprint arXiv:2408.08872 (2024)"},{"key":"20_CR24","unstructured":"Zhang, S., Xu, Y., Usuyama, N., Xu, H., Bagga, J., Tinn, R., Preston, S., Rao, R., Wei, M., Valluri, N., et\u00a0al.: Biomedclip: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs. arXiv preprint arXiv:2303.00915 (2023)"}],"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\/978-3-032-04981-0_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,3]],"date-time":"2026-01-03T05:33:39Z","timestamp":1767418419000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04981-0_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,20]]},"ISBN":["9783032049803","9783032049810"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04981-0_20","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"}}]}}