{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T07:09:37Z","timestamp":1779347377540,"version":"3.51.4"},"reference-count":29,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,4,8]]},"DOI":"10.1109\/isbi61048.2026.11515599","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":["Gaze2Report: Radiology Report Generation via Visual-Gaze Prompt Tuning of LLMs"],"prefix":"10.1109","author":[{"given":"Aishik","family":"Konwer","sequence":"first","affiliation":[{"name":"Stony Brook University,Stony Brook,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Moinak","family":"Bhattacharya","sequence":"additional","affiliation":[{"name":"Stony Brook University,Stony Brook,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Prateek","family":"Prasanna","sequence":"additional","affiliation":[{"name":"Stony Brook University,Stony Brook,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3171661"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01354"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref4","article-title":"Unimo: Towards unified-modal understanding and generation via cross-modal contrastive learning","author":"Li","year":"2020","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00251"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2024.3354712"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16437-8_66"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_40"},{"key":"ref9","article-title":"Gazediff: a radiologist visual attention guided diffusion model for zero-shot disease classification","author":"Bhattacharya","year":"2024","journal-title":"MIDL"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2024.3422168"},{"key":"ref11","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref12","author":"Awasthi","year":"2024","journal-title":"Multimodal learning and cognitive processes in radiology: Medgaze for chest x-ray scanpath prediction"},{"key":"ref13","article-title":"Vision gnn: An image is worth graph of nodes","author":"Han","year":"2022","journal-title":"NeurIPS"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref15","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"Xu","year":"2015","journal-title":"ICML"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_33"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01112"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.metrad.2023.100033"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01441-z"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocv080"},{"key":"ref23","article-title":"Mimic-cxr-jpg, a large publicly available database of labeled chest radiographs","author":"EW Johnson","year":"2019","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"ref25","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"Papineni","year":"2002","journal-title":"ACL"},{"key":"ref26","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume-title":"ACL workshop","author":"Banerjee"},{"key":"ref27","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.117"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.319"}],"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\/11515599.pdf?arnumber=11515599","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T06:26:44Z","timestamp":1779344804000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11515599\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,8]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/isbi61048.2026.11515599","relation":{},"subject":[],"published":{"date-parts":[[2026,4,8]]}}}