{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T08:38:13Z","timestamp":1785487093000,"version":"3.56.0"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031806063","type":"print"},{"value":"9783031806070","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\/978-3-031-80607-0_22","type":"book-chapter","created":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T16:34:40Z","timestamp":1735662880000},"page":"288-300","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["DR-Minerva: A\u00a0Multimodal Language Model Based on\u00a0Minerva for\u00a0Diagnostic Information Retrieval"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8434-8729","authenticated-orcid":false,"given":"Irene","family":"Siragusa","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7476-1545","authenticated-orcid":false,"given":"Salvatore","family":"Contino","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9453-510X","authenticated-orcid":false,"given":"Roberto","family":"Pirrone","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,1,1]]},"reference":[{"key":"22_CR1","unstructured":"Medpix. https:\/\/medpix.nlm.nih.gov\/home"},{"key":"22_CR2","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning (2022)"},{"key":"22_CR3","unstructured":"Awadalla, A., et al.: Openflamingo: an open-source framework for training large autoregressive vision-language models. arXiv preprint arXiv:2308.01390 (2023)"},{"key":"22_CR4","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"2","key":"22_CR5","doi-asserted-by":"publisher","first-page":"94","DOI":"10.7861\/futurehosp.6-2-94","volume":"6","author":"T Davenport","year":"2019","unstructured":"Davenport, T., Kalakota, R.: The potential for artificial intelligence in healthcare. Fut. Healthc. J. 6(2), 94\u201398 (2019). https:\/\/doi.org\/10.7861\/futurehosp.6-2-94","journal-title":"Fut. Healthc. J."},{"key":"22_CR6","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"22_CR7","unstructured":"Douze, M., et al.: The Faiss library (2024). https:\/\/arxiv.org\/abs\/2401.08281"},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"Hartsock, I., Rasool, G.: Vision-language models for medical report generation and visual question answering: a review. arXiv preprint arXiv:2403.02469 (2024)","DOI":"10.3389\/frai.2024.1430984"},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"He, X., Zhang, Y., Mou, L., Xing, E., Xie, P.: Pathvqa: 30000+ questions for medical visual question answering. arXiv preprint arXiv:2003.10286 (2020)","DOI":"10.36227\/techrxiv.13127537.v1"},{"key":"22_CR10","unstructured":"Hromei, C.D., Croce, D., Basile, V., Basili, R.: Extremita at evalita 2023: multi-task sustainable scaling to large language models at its extreme. In: Proceedings of the Eighth Evaluation Campaign of Natural Language Processing and Speech Tools for Italian. Final Workshop (EVALITA 2023), Parma, Italy. CEUR.org (2023)"},{"key":"22_CR11","unstructured":"Jack\u00a0Jr, C.R., et\u00a0al.: The Alzheimer\u2019s disease neuroimaging initiative (ADNI): MRI methods. J. Magn. Reson. Imaging Off. J. Int. Soc. Magn. Reson. Med. 27(4), 685\u2013691 (2008)"},{"issue":"1","key":"22_CR12","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1038\/s41597-019-0322-0","volume":"6","author":"AE Johnson","year":"2019","unstructured":"Johnson, A.E., et al.: Mimic-CXR, a de-identified publicly available database of chest radiographs with free-text reports. Sci. Data 6(1), 317 (2019)","journal-title":"Sci. Data"},{"key":"22_CR13","unstructured":"Junseong, K., et al.: Linq-embed-mistral:elevating text retrieval with improved gpt data through task-specific control and quality refinement. Linq AI Res. Blog (2024). https:\/\/getlinq.com\/blog\/linq-embed-mistral\/"},{"issue":"1","key":"22_CR14","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. Sci. Data 5(1), 1\u201310 (2018)","journal-title":"Sci. Data"},{"key":"22_CR15","unstructured":"Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive NLP tasks. Adv. Neural. Inf. Process. Syst. 33, 9459\u20139474 (2020)"},{"key":"22_CR16","doi-asserted-by":"crossref","unstructured":"Li, C., et al.: Llava-med: training a large language-and-vision assistant for biomedicine in one day. In: Advances in Neural Information Processing Systems, vol. 36 (2024)","DOI":"10.32388\/VLXB6M"},{"key":"22_CR17","doi-asserted-by":"publisher","unstructured":"Lin, W., et al.: PMC-clip: contrastive language-image pre-training using biomedical documents. In: Greenspan, H., et al. (eds.) MICCAI 2023. LNCS, vol. 14227, pp. 525\u2013536. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-43993-3_51","DOI":"10.1007\/978-3-031-43993-3_51"},{"key":"22_CR18","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":"22_CR19","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"22_CR20","unstructured":"Llama\u00a0Team, A..M.: The llama 3 herd of models (2024). https:\/\/arxiv.org\/abs\/2407.21783"},{"key":"22_CR21","unstructured":"Moor, M., et al.: Med-flamingo: a multimodal medical few-shot learner. In: Machine Learning for Health (ML4H), pp. 353\u2013367. PMLR (2023)"},{"key":"22_CR22","doi-asserted-by":"publisher","unstructured":"Muennighoff, N., Tazi, N., Magne, L., Reimers, N.: MTEB: massive text embedding benchmark. arXiv preprint arXiv:2210.07316 (2022).https:\/\/doi.org\/10.48550\/ARXIV.2210.07316, https:\/\/arxiv.org\/abs\/2210.07316","DOI":"10.48550\/ARXIV.2210.07316"},{"key":"22_CR23","unstructured":"Orlando, R., Moroni, L., Huguet\u00a0Cabot, P.L., Conia, S., Barba, E., Navigli, R.: Minerva technical report (2024). https:\/\/nlp.uniroma1.it\/minerva\/"},{"key":"22_CR24","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision (2021)"},{"issue":"4","key":"22_CR25","doi-asserted-by":"publisher","first-page":"1291","DOI":"10.1007\/s10278-022-00767-9","volume":"36","author":"P Raffy","year":"2023","unstructured":"Raffy, P., Pambrun, J.F., Kumar, A., Dubois, D., Patti, J.W., Cairns, R.A., Young, R.: Deep learning body region classification of MRI and CT examinations. J. Digit. Imaging 36(4), 1291\u20131301 (2023). https:\/\/doi.org\/10.1007\/s10278-022-00767-9","journal-title":"J. Digit. Imaging"},{"key":"22_CR26","unstructured":"Siragusa, I., Contino, S., Ciura, M.L., Alicata, R., Pirrone, R.: Medpix 2.0: a comprehensive multimodal biomedical dataset for advanced AI applications. In: Proceedings of the 3rd Italian Conference on Big Data and Data Science, ITADATA2024 (to appear). Pisa, Italy (2024). https:\/\/arxiv.org\/abs\/2407.02994"},{"key":"22_CR27","unstructured":"Touvron, H., et al.: Llama 2: open foundation and fine-tuned chat models (2023)"},{"key":"22_CR28","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"22_CR29","unstructured":"Zhang, S., 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","AIxIA 2024 \u2013 Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-80607-0_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T17:05:44Z","timestamp":1735664744000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-80607-0_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031806063","9783031806070"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-80607-0_22","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":"1 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors declares that they have no relevant or material financial interests that relate to the research described in this paper.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"AIxIA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference of the Italian Association for Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bolzano","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"24 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aiia2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}