{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T07:08:33Z","timestamp":1779347313760,"version":"3.51.4"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T00:00:00Z","timestamp":1775606400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T00:00:00Z","timestamp":1775606400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018542","name":"Natural Science Foundation of Sichuan","doi-asserted-by":"publisher","award":["2025ZNSFSC0455"],"award-info":[{"award-number":["2025ZNSFSC0455"]}],"id":[{"id":"10.13039\/501100018542","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,4,8]]},"DOI":"10.1109\/isbi61048.2026.11515779","type":"proceedings-article","created":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T19:48:46Z","timestamp":1779306526000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["REAF: a Region-Enhanced Volume-Slice Hierarchical Attention Fusion Vision-Language Model for CT-Report Retrieval"],"prefix":"10.1109","author":[{"given":"Jinlong","family":"He","sequence":"first","affiliation":[{"name":"School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China,Chengdu,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China,Chengdu,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guotai","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China,Chengdu,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"21108","article-title":"LIM-ITR: leveraging local information for medical imagetext representation","volume-title":"in ICCV","author":"Dawidowicz"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3590930"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI56570.2024.10635576"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103553"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI60581.2025.10981079"},{"key":"ref6","article-title":"M3D: advancing 3D medical image analysis with multi-modal large language models","volume":"abs\/2404.00578","author":"Bai","year":"2024","journal-title":"CoRR"},{"key":"ref7","article-title":"Developing generalist foundation models from a multimodal dataset for 3D computed tomography","author":"Ethem Hamamci","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"An image is worth $16 \\times 16$ words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"in ICLR"},{"key":"ref9","article-title":"Merlin: A vision language foundation model for 3D computed tomography","volume":"abs\/2406.06512","author":"Blankemeier","year":"2024","journal-title":"CoRR"},{"key":"ref10","article-title":"Hsenet: Hybrid spatial encoding network for 3D medical vision-language understanding","volume":"abs\/2506.09634","author":"Shi","year":"2025","journal-title":"CoRR"},{"key":"ref11","article-title":"Towards scalable language-image pre-training for 3D medical imaging","volume":"abs\/2505.21862","author":"Zhao","year":"2025","journal-title":"CoRR"},{"key":"ref12","article-title":"T3D: Towards 3D medical image understanding through vision-language pre-training","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"MG-3D: multi-grained knowledge-enhanced 3D medical vision-language pretraining","volume":"abs\/2412.05876","author":"Ni","year":"2024","journal-title":"CoRR"},{"key":"ref14","article-title":"Med3DVLM: An efficient vision-language model for 3D medical image analysis","volume":"abs\/2503.20047","author":"Xin","year":"2025","journal-title":"CoRR"},{"key":"ref15","first-page":"2","article-title":"Contrastive learning of medical visual representations from paired images and text","volume-title":"in MLHC","volume":"182","author":"Zhang"},{"key":"ref16","article-title":"Large-scale and fine-grained vision-language pre-training for enhanced CT image understanding","author":"Shui","year":"2025","journal-title":"in ICLR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01068"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3458754"},{"key":"ref19","first-page":"7949","article-title":"Robust finetuning of zero-shot models","volume-title":"in CVPR","author":"Wortsman"}],"event":{"name":"2026 IEEE 23rd International Symposium on Biomedical Imaging (ISBI)","location":"London, United Kingdom","start":{"date-parts":[[2026,4,8]]},"end":{"date-parts":[[2026,4,11]]}},"container-title":["2026 IEEE 23rd International Symposium on Biomedical Imaging (ISBI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11515282\/11515297\/11515779.pdf?arnumber=11515779","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T06:24:38Z","timestamp":1779344678000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11515779\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,8]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/isbi61048.2026.11515779","relation":{},"subject":[],"published":{"date-parts":[[2026,4,8]]}}}