{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T15:30:16Z","timestamp":1777735816629,"version":"3.51.4"},"reference-count":75,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62125201"],"award-info":[{"award-number":["62125201"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62020106007"],"award-info":[{"award-number":["62020106007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62002314"],"award-info":[{"award-number":["62002314"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62406093"],"award-info":[{"award-number":["62406093"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LY23F020005"],"award-info":[{"award-number":["LY23F020005"]}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LQ24F020032"],"award-info":[{"award-number":["LQ24F020032"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Biomed. Health Inform."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/jbhi.2025.3535699","type":"journal-article","created":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T18:44:26Z","timestamp":1738089866000},"page":"5303-5316","source":"Crossref","is-referenced-by-count":9,"title":["Adapter-Enhanced Hierarchical Cross-Modal Pre-Training for Lightweight Medical Report Generation"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4348-2671","authenticated-orcid":false,"given":"Ting","family":"Yu","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, Hangzhou Normal University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0878-6433","authenticated-orcid":false,"given":"Wangwen","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Hangzhou Normal University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5598-1692","authenticated-orcid":false,"given":"Yan","family":"Yang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7227-3671","authenticated-orcid":false,"given":"Weidong","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Colorectal Medical Oncology, Zhejiang Cancer Hospital, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7542-296X","authenticated-orcid":false,"given":"Qingming","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}]},{"given":"Jun","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9855-003X","authenticated-orcid":false,"given":"Ke","family":"Zhang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Complex Systems Modeling and Simulation, School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.459"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01112"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00325"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87199-4_7"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102510"},{"key":"ref7","first-page":"1","article-title":"An image is worth 16  16 words: Transformers for image recognition at scale","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref8","first-page":"68","article-title":"Stand-alone self-attention in vision models","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Ramachandran","year":"2019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3152247"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref13","article-title":"Vision transformer adapter for dense predictions","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Chen","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01364-6_20"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.191"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43993-3_51"},{"key":"ref17","first-page":"2","article-title":"Contrastive learning of medical visual representations from paired images and text","volume-title":"Proc. Mach. Learn. Healthcare Conf.","author":"Zhang","year":"2022"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"ref19","first-page":"33536","article-title":"Multi-granularity cross-modal alignment for generalized medical visual representation learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Wang","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01953"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-40260-7"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16258"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref30","first-page":"11137","article-title":"Image captioning: Transforming objects into words","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Herdade","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02237"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00278"},{"key":"ref34","first-page":"1537","article-title":"Hybrid retrieval-generation reinforced agent for medical image report generation","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Li","year":"2018"},{"key":"ref35","first-page":"249","article-title":"Clinically accurate chest X-ray report generation","volume-title":"Proc. Mach. Learn. Healthcare Conf.","author":"Liu","year":"2019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87234-2_28"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6989"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01354"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016666"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3273390"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01897"},{"key":"ref42","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref44","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocv080"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0052-1"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.23"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.38"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3614961"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.metrad.2023.100033"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20204"},{"key":"ref53","article-title":"Radialog: A large vision-language model for radiology report generation and conversational assistance","author":"Pellegrini","year":"2023"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00718"},{"key":"ref55","article-title":"Towards generalist foundation model for radiology","author":"Wu","year":"2023"},{"key":"ref56","article-title":"LLM-CXR: Instruction-finetuned LLM for CXR image understanding and generation","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Lee","year":"2024"},{"key":"ref57","article-title":"The dawn of LMMs: Preliminary explorations with GPT-4V (ision)","author":"Yang","year":"2023"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-03185-2"},{"key":"ref59","article-title":"Cross-modal causal intervention for medical report generation","author":"Chen","year":"2023"},{"key":"ref60","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke","year":"2019"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref62","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref64","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Workshop Text Summarization Branches Out, Post-Conf. Workshop","author":"Lin","year":"2004"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.3115\/1626355.1626389"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref67","article-title":"BERTScore: Evaluating text generation with BERT","author":"Zhang","year":"2019"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.117"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2023.100802"},{"key":"ref70","article-title":"Radgraph: Extracting clinical entities and relations from radiology reports","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track (Round 1)","author":"Jain","year":"2021"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.836"},{"key":"ref72","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref73","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref74","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"issue":"70","key":"ref75","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","year":"2024","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Journal of Biomedical and Health Informatics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221020\/11068702\/10856362.pdf?arnumber=10856362","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T04:42:50Z","timestamp":1751604170000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10856362\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":75,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/jbhi.2025.3535699","relation":{},"ISSN":["2168-2194","2168-2208"],"issn-type":[{"value":"2168-2194","type":"print"},{"value":"2168-2208","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}