{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T07:10:01Z","timestamp":1779347401490,"version":"3.51.4"},"reference-count":16,"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\/isbi61048.2026.11516032","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":["When Vision-Language Models Look but Don't See: Anatomical Bias in Endoscopic Spatial Reasoning"],"prefix":"10.1109","author":[{"given":"Diego","family":"Bravo","sequence":"first","affiliation":[{"name":"Universidad Nacional de Colombia,Computer Imaging and Medical Applications Laboratory (CIM@LAB)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Wolf","sequence":"additional","affiliation":[{"name":"Institute of Media Informatics, Ulm University,Visual Computing Group,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juan","family":"Hurtado-Tobar","sequence":"additional","affiliation":[{"name":"Universidad Nacional de Colombia,Computer Imaging and Medical Applications Laboratory (CIM@LAB)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mart\u00edn","family":"G\u00f3mez","sequence":"additional","affiliation":[{"name":"Universidad Nacional de Colombia,Computer Imaging and Medical Applications Laboratory (CIM@LAB)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eduardo","family":"Romero","sequence":"additional","affiliation":[{"name":"Universidad Nacional de Colombia,Computer Imaging and Medical Applications Laboratory (CIM@LAB)"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"1","key":"ref1","first-page":"11","article-title":"The endoscopic diagnosis of early gastric cancer","volume-title":"Annals of Gastroenterology: Quarterly Publication of the Hellenic Society of Gastroenterology","volume":"26","author":"Yao","year":"2013"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3748\/wjg.v21.i8.2460"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3748\/wjg.v21.i3.759"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101900"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1055\/s-0034-1365524"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.bpg.2015.05.010"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-04971-1_65"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-025-04401-5"},{"key":"ref9","article-title":"GastroHun: an endoscopy dataset of complete systematic screening protocol for the stomach","author":"Bravo","year":"2025","journal-title":"Figshare"},{"key":"ref10","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities","author":"Comanici","year":"2025","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Janus-pro-7b","volume-title":"DeepSeek-AI","year":"2025"},{"key":"ref13","first-page":"arXiv","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv e-prints"},{"key":"ref14","article-title":"Llama-3.2\u201311b-vision-instruct","volume-title":"Meta","year":"2024"},{"key":"ref15","article-title":"6 fingers, 1 kidney: Natural adversarial medical images reveal critical weaknesses of vision-language models","author":"Mayer","year":"2025","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Ethics and governance of artificial intelligence for health: large multi-modal models","year":"2024","journal-title":"WHO guidance, World Health Organization"}],"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\/11516032.pdf?arnumber=11516032","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T06:31:47Z","timestamp":1779345107000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11516032\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,8]]},"references-count":16,"URL":"https:\/\/doi.org\/10.1109\/isbi61048.2026.11516032","relation":{},"subject":[],"published":{"date-parts":[[2026,4,8]]}}}