{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T15:56:06Z","timestamp":1776268566192,"version":"3.50.1"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031845246","type":"print"},{"value":"9783031845253","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-84525-3_18","type":"book-chapter","created":{"date-parts":[[2025,4,12]],"date-time":"2025-04-12T06:22:36Z","timestamp":1744438956000},"page":"211-222","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["MedPromptX: Grounded Multimodal Prompting for\u00a0Chest X-Ray Diagnosis"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1454-6090","authenticated-orcid":false,"given":"Mai A.","family":"Shaaban","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0583-9863","authenticated-orcid":false,"given":"Adnan","family":"Khan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6896-1105","authenticated-orcid":false,"given":"Mohammad","family":"Yaqub","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,13]]},"reference":[{"key":"18_CR1","unstructured":"Alayrac, J.B., Donahue, J., Luc, P., et\u00a0al.: Flamingo: a visual language model for few-shot learning. In: Advances in Neural Information Processing Systems, vol. 35 (2022). https:\/\/arxiv.org\/abs\/2204.14198v2"},{"key":"18_CR2","unstructured":"Awadalla, A., Gao, I., Gardner, J., et\u00a0al.: OpenFlamingo: an open-source framework for training large autoregressive vision-language models. arXiv preprint arXiv:2308.01390 (2023)"},{"key":"18_CR3","unstructured":"Bolton, E., Hall, D., Yasunaga, M., et\u00a0al.: Stanford CRFM: Biomedlm (2022). https:\/\/crfm.stanford.edu\/2022\/12\/15\/biomedlm.html"},{"key":"18_CR4","unstructured":"Brown, T.B., Mann, B., Ryder, N., et\u00a0al.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems, vol. 2020-Decem (2020). https:\/\/arxiv.org\/abs\/2005.14165v4"},{"key":"18_CR5","unstructured":"Devlin, J., Chang, M.W., Lee, K., et\u00a0al.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"18_CR6","doi-asserted-by":"publisher","unstructured":"Ichinose, A., Hatsutani, T., Nakamura, K., et\u00a0al.: Visual grounding of whole radiology reports for 3D CT images, p. 611\u2013621. Springer Nature Switzerland (2023). https:\/\/doi.org\/10.1007\/978-3-031-43904-9_59","DOI":"10.1007\/978-3-031-43904-9_59"},{"key":"18_CR7","unstructured":"Johnson, A.E.W., Pollard, T.J., Greenbaum, N.R., et\u00a0al.: MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs (2019). https:\/\/arxiv.org\/abs\/1901.07042v5"},{"key":"18_CR8","doi-asserted-by":"publisher","unstructured":"Johnson, A.E., Bulgarelli, L., Shen, L., et\u00a0al.: MIMIC-IV, a freely accessible electronic health record dataset. Sci. Data 10(1), 1\u20139 (2023). https:\/\/doi.org\/10.1038\/s41597-022-01899-x","DOI":"10.1038\/s41597-022-01899-x"},{"key":"18_CR9","doi-asserted-by":"publisher","unstructured":"van Leeuwen, K.G., de Rooij, M., Schalekamp, S., van Ginneken, B., Rutten, M.J.C.M.: How does artificial intelligence in radiology improve efficiency and health outcomes? Pediatr. Radiol., 1\u20137 (2021). https:\/\/doi.org\/10.1007\/s00247-021-05114-8","DOI":"10.1007\/s00247-021-05114-8"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Li, L.H., Zhang, P., Zhang, H., et\u00a0al.: Grounded language-image pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10965\u201310975 (2022)","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Li, Y., Liu, Y., Wang, Z., et\u00a0al.: A comprehensive study of GPT-4V\u2019s multimodal capabilities in medical imaging. medRxiv, pp. 2023\u201311 (2023)","DOI":"10.1101\/2023.11.03.23298067"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Liu, S., Zeng, Z., Ren, T., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., et\u00a0al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"18_CR14","doi-asserted-by":"publisher","unstructured":"Lu, Q., Dou, D., Nguyen, T.H.: ClinicalT5: a generative language model for clinical text. findings of the association for computational linguistics: EMNLP 2022, pp. 5436\u20135443 (2022). https:\/\/doi.org\/10.18653\/V1\/2022.FINDINGS-EMNLP.398","DOI":"10.18653\/V1\/2022.FINDINGS-EMNLP.398"},{"key":"18_CR15","unstructured":"Moor, M., Huang, Q., Wu, S., et\u00a0al.: Med-Flamingo: a multimodal medical few-shot learner (2023). https:\/\/arxiv.org\/abs\/2307.15189v1"},{"issue":"17","key":"18_CR16","doi-asserted-by":"publisher","first-page":"2760","DOI":"10.3390\/diagnostics13172760","volume":"13","author":"R Najjar","year":"2023","unstructured":"Najjar, R.: Redefining radiology: a review of artificial intelligence integration in medical imaging. Diagnostics 13(17), 2760 (2023)","journal-title":"Diagnostics"},{"key":"18_CR17","unstructured":"Radford, A., Kim, J.W., Hallacy, C., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"18_CR18","doi-asserted-by":"publisher","first-page":"136947","DOI":"10.1109\/ACCESS.2020.3011099","volume":"8","author":"SM Shah","year":"2020","unstructured":"Shah, S.M., Khan, R.A.: Secondary use of electronic health record: opportunities and challenges. IEEE Access 8, 136947\u2013136965 (2020)","journal-title":"IEEE Access"},{"key":"18_CR19","doi-asserted-by":"publisher","unstructured":"Soenksen, L.R., Ma, Y., Zeng, C., et\u00a0al.: Integrated multimodal artificial intelligence framework for healthcare applications. NPJ Digit. Med. 5(1), 1\u201310 (2022). https:\/\/doi.org\/10.1038\/s41746-022-00689-4","DOI":"10.1038\/s41746-022-00689-4"},{"key":"18_CR20","unstructured":"Touvron, H., Lavril, T., Izacard, G., et\u00a0al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Tu, T., Azizi, S., Driess, D., et\u00a0al.: Towards generalist biomedical AI (2023). https:\/\/arxiv.org\/abs\/2307.14334v1","DOI":"10.1056\/AIoa2300138"},{"key":"18_CR22","unstructured":"Yang, Z., Gan, Z., Wang, J., et\u00a0al.: An empirical study of GPT-3 for few-shot knowledge-based VQA"},{"key":"18_CR23","doi-asserted-by":"publisher","unstructured":"Yin, S., Fu, C., Zhao, S., et\u00a0al.: Woodpecker: hallucination correction for multimodal large language models (2023). https:\/\/doi.org\/10.48550\/ARXIV.2310.16045","DOI":"10.48550\/ARXIV.2310.16045"},{"key":"18_CR24","unstructured":"Zhang, H., Li, F., Liu, S., et\u00a0al.: Dino: DETR with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605 (2022)"},{"key":"18_CR25","unstructured":"Zhang, K., Yu, J., Adhikarla, E., et\u00a0al.: BiomedGPT: a unified and generalist biomedical generative pre-trained transformer for vision, language, and multimodal tasks (2024)"},{"key":"18_CR26","unstructured":"Zhou, H., Liu, F., Gu, B., et\u00a0al.: A survey of large language models in medicine: principles, applications, and challenges (2023). https:\/\/arxiv.org\/abs\/2311.05112v2"},{"key":"18_CR27","unstructured":"Zhu, Y., et al.: Prompting large language models for zero-shot clinical prediction with structured longitudinal electronic health record data. arXiv preprint arXiv:2402.01713 (2024)"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-84525-3_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,12]],"date-time":"2025-04-12T06:22:49Z","timestamp":1744438969000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-84525-3_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031845246","9783031845253"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-84525-3_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"13 April 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"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":"Marrakesh","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Morocco","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2024\/en\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}