{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T05:53:52Z","timestamp":1767678832475,"version":"3.48.0"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/aiccsa66935.2025.11315275","type":"proceedings-article","created":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:35:55Z","timestamp":1767638155000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Structured Comprehensive Textual Representations for Medical Vision-Language Pretraining"],"prefix":"10.1109","author":[{"given":"Youssef","family":"Ibrahim","sequence":"first","affiliation":[{"name":"Khalifa University Abu,Computer Science Department,Dhabi,UAE"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anabia","family":"Sohail","sequence":"additional","affiliation":[{"name":"Khalifa University Abu,Computer Science Department,Dhabi,UAE"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sajid","family":"Javed","sequence":"additional","affiliation":[{"name":"Khalifa University Abu,Computer Science Department,Dhabi,UAE"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hasan Al","family":"Marzouqi","sequence":"additional","affiliation":[{"name":"Khalifa University Abu,Computer Science Department,Dhabi,UAE"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naoufel","family":"Werghi","sequence":"additional","affiliation":[{"name":"Khalifa University Abu,Computer Science Department,Dhabi,UAE"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"19730","article-title":"Blip-2: Bootstrapping languageimage pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref2","article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning. arxiv 2023","volume":"2","author":"Dai","year":"2023","journal-title":"arXiv preprint arXiv:2305.06500"},{"key":"ref3","article-title":"Towards generalist foundation model for radiology","author":"Wu","year":"2023","journal-title":"arXiv preprint arXiv:2308.02463"},{"key":"ref4","article-title":"Llava-med: Training a large language-and-vision assistant for biomedicine in one day","volume":"36","author":"Li","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Gatortron: A large clinical language model to unlock patient information from unstructured electronic health records","year":"2022","author":"Yang","key":"ref5"},{"issue":"7972","key":"ref6","first-page":"1723180A","article-title":"Large language models encode clinical knowledge","volume-title":"SubjectsTermNotLitGenreText-Social","volume":"620","author":"Singhal"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-05881-4"},{"volume-title":"Radiopaedia","year":"2025","key":"ref8"},{"article-title":"Pubmed","year":"2025","author":"of Medicine","key":"ref9"},{"key":"ref10","first-page":"353","article-title":"Med-flamingo: a multimodal medical few-shot learner","author":"Moor","year":"2023","journal-title":"Machine Learning for Health (ML4H)"},{"key":"ref11","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","article-title":"A generalist agent","author":"Reed","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.bionlp-1.35"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01088"},{"key":"ref15","article-title":"Biomedclip: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv:2303.00915"},{"key":"ref16","article-title":"Mimic-cxr-jpg-chest radiographs with structured labels","author":"Johnson","year":"2019","journal-title":"PhysioNet"},{"key":"ref17","article-title":"Chexagent: Towards a foundation model for chest x-ray interpretation","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv:2401.12208"}],"event":{"name":"2025 IEEE\/ACS 22nd International Conference on Computer Systems and Applications (AICCSA)","start":{"date-parts":[[2025,10,19]]},"location":"Doha, Qatar","end":{"date-parts":[[2025,10,22]]}},"container-title":["2025 IEEE\/ACS 22nd International Conference on Computer Systems and Applications (AICCSA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11315137\/11315140\/11315275.pdf?arnumber=11315275","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T05:51:36Z","timestamp":1767678696000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11315275\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/aiccsa66935.2025.11315275","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}