{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T07:45:30Z","timestamp":1785829530641,"version":"3.56.0"},"reference-count":40,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100018625","name":"Science and Technology Innovation Plan Of Shanghai Science and Technology Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018625","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100031931","name":"Shanghai Artificial Intelligence Laboratory","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100031931","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013098","name":"Scientific and Innovative Action Plan of Shanghai","doi-asserted-by":"publisher","award":["2023DFYCQN02"],"award-info":[{"award-number":["2023DFYCQN02"]}],"id":[{"id":"10.13039\/501100013098","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Medical Image Analysis"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.media.2026.104196","type":"journal-article","created":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T15:23:59Z","timestamp":1783351439000},"page":"104196","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["OmniPathoVQA: Benchmarking pathology vision\u2013language models with Encyclopedia-scale knowledge"],"prefix":"10.1016","volume":"113","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8422-7920","authenticated-orcid":false,"given":"Kaitao","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linda","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaohao","family":"Rui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifan","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xialing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zunguo","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ping","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mianxin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5072-5630","authenticated-orcid":false,"given":"Mu","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8325-3596","authenticated-orcid":false,"given":"Yirong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.media.2026.104196_b1","series-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"10.1016\/j.media.2026.104196_b2","series-title":"Qwen technical report","author":"Bai","year":"2023"},{"key":"10.1016\/j.media.2026.104196_b3","series-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025"},{"issue":"3","key":"10.1016\/j.media.2026.104196_b4","doi-asserted-by":"crossref","first-page":"850","DOI":"10.1038\/s41591-024-02857-3","article-title":"Towards a general-purpose foundation model for computational pathology","volume":"30","author":"Chen","year":"2024","journal-title":"Nature Med."},{"key":"10.1016\/j.media.2026.104196_b5","series-title":"Huatuogpt-vision, towards injecting medical visual knowledge into multimodal llms at scale","author":"Chen","year":"2024"},{"key":"10.1016\/j.media.2026.104196_b6","first-page":"1","article-title":"Cost-effective instruction learning for pathology vision and language analysis","author":"Chen","year":"2025","journal-title":"Nat. Comput. Sci."},{"key":"10.1016\/j.media.2026.104196_b7","series-title":"Think twice to see more: Iterative visual reasoning in medical VLMs","author":"Chen","year":"2025"},{"key":"10.1016\/j.media.2026.104196_b8","series-title":"European Conference on Computer Vision","first-page":"401","article-title":"Wsi-vqa: Interpreting whole slide images by generative visual question answering","author":"Chen","year":"2024"},{"key":"10.1016\/j.media.2026.104196_b9","series-title":"Claude sonnet 4","author":"Claude","year":"2025"},{"key":"10.1016\/j.media.2026.104196_b10","series-title":"Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities","author":"Comanici","year":"2025"},{"key":"10.1016\/j.media.2026.104196_b11","series-title":"Advances in Neural Information Processing Systems","article-title":"FlashAttention: Fast and memory-efficient exact attention with IO-awareness","author":"Dao","year":"2022"},{"key":"10.1016\/j.media.2026.104196_b12","first-page":"1","article-title":"A multimodal whole-slide foundation model for pathology","author":"Ding","year":"2025","journal-title":"Nature Med."},{"key":"10.1016\/j.media.2026.104196_b13","series-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"issue":"8081","key":"10.1016\/j.media.2026.104196_b14","doi-asserted-by":"crossref","first-page":"633","DOI":"10.1038\/s41586-025-09422-z","article-title":"Deepseek-r1 incentivizes reasoning in llms through reinforcement learning","volume":"645","author":"Guo","year":"2025","journal-title":"Nature"},{"key":"10.1016\/j.media.2026.104196_b15","series-title":"Pathvqa: 30000+ questions for medical visual question answering","author":"He","year":"2020"},{"key":"10.1016\/j.media.2026.104196_b16","series-title":"Hulu-med: A transparent generalist model towards holistic medical vision-language understanding","author":"Jiang","year":"2025"},{"key":"10.1016\/j.media.2026.104196_b17","doi-asserted-by":"crossref","unstructured":"Kwon, W., Li, Z., Zhuang, S., Sheng, Y., Zheng, L., Yu, C.H., Gonzalez, J.E., Zhang, H., Stoica, I., 2023. Efficient Memory Management for Large Language Model Serving with PagedAttention. In: Proceedings of the ACM SIGOPS Symposium on Operating Systems Principles.","DOI":"10.1145\/3600006.3613165"},{"issue":"1","key":"10.1016\/j.media.2026.104196_b18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/sdata.2018.251","article-title":"A dataset of clinically generated visual questions and answers about radiology images","volume":"5","author":"Lau","year":"2018","journal-title":"Sci. Data"},{"key":"10.1016\/j.media.2026.104196_b19","doi-asserted-by":"crossref","first-page":"28541","DOI":"10.52202\/075280-1240","article-title":"Llava-med: Training a large language-and-vision assistant for biomedicine in one day","volume":"36","author":"Li","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2026.104196_b20","doi-asserted-by":"crossref","first-page":"34892","DOI":"10.52202\/075280-1516","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.media.2026.104196_b21","series-title":"2021 IEEE 18th International Symposium on Biomedical Imaging","first-page":"1650","article-title":"Slake: A semantically-labeled knowledge-enhanced dataset for medical visual question answering","author":"Liu","year":"2021"},{"issue":"8033","key":"10.1016\/j.media.2026.104196_b22","doi-asserted-by":"crossref","first-page":"466","DOI":"10.1038\/s41586-024-07618-3","article-title":"A multimodal generative AI copilot for human pathology","volume":"634","author":"Lu","year":"2024","journal-title":"Nature"},{"key":"10.1016\/j.media.2026.104196_b23","series-title":"OpenAI o3 and o4-mini System Card","author":"OpenAI","year":"2025"},{"key":"10.1016\/j.media.2026.104196_b24","series-title":"GPT-5 system card","author":"OpenAI","year":"2025"},{"key":"10.1016\/j.media.2026.104196_b25","series-title":"Medgemma technical report","author":"Sellergren","year":"2025"},{"key":"10.1016\/j.media.2026.104196_b26","doi-asserted-by":"crossref","unstructured":"Seyfioglu, M.S., Ikezogwo, W.O., Ghezloo, F., Krishna, R., Shapiro, L., 2024a. Quilt-llava: Visual instruction tuning by extracting localized narratives from open-source histopathology videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 13183\u201313192.","DOI":"10.1109\/CVPR52733.2024.01252"},{"key":"10.1016\/j.media.2026.104196_b27","doi-asserted-by":"crossref","unstructured":"Seyfioglu, M.S., Ikezogwo, W.O., Ghezloo, F., Krishna, R., Shapiro, L., 2024b. Quilt-llava: Visual instruction tuning by extracting localized narratives from open-source histopathology videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 13183\u201313192.","DOI":"10.1109\/CVPR52733.2024.01252"},{"key":"10.1016\/j.media.2026.104196_b28","series-title":"European Conference on Computer Vision","first-page":"56","article-title":"Pathmmu: A massive multimodal expert-level benchmark for understanding and reasoning in pathology","author":"Sun","year":"2024"},{"key":"10.1016\/j.media.2026.104196_b29","series-title":"Pathgen-1.6 m: 1.6 million pathology image-text pairs generation through multi-agent collaboration","author":"Sun","year":"2024"},{"issue":"1","key":"10.1016\/j.media.2026.104196_b30","doi-asserted-by":"crossref","first-page":"68","DOI":"10.5114\/wo.2014.47136","article-title":"Review the cancer genome atlas (TCGA): an immeasurable source of knowledge","volume":"2015","author":"Tomczak","year":"2015","journal-title":"Contemp. Oncol.\/Wsp\u00f3\u0142Czesna Onkol."},{"issue":"10","key":"10.1016\/j.media.2026.104196_b31","doi-asserted-by":"crossref","first-page":"2924","DOI":"10.1038\/s41591-024-03141-0","article-title":"A foundation model for clinical-grade computational pathology and rare cancers detection","volume":"30","author":"Vorontsov","year":"2024","journal-title":"Nature Med."},{"key":"10.1016\/j.media.2026.104196_b32","series-title":"MinerU: An open-source solution for precise document content extraction","author":"Wang","year":"2024"},{"issue":"8035","key":"10.1016\/j.media.2026.104196_b33","doi-asserted-by":"crossref","first-page":"970","DOI":"10.1038\/s41586-024-07894-z","article-title":"A pathology foundation model for cancer diagnosis and prognosis prediction","volume":"634","author":"Wang","year":"2024","journal-title":"Nature"},{"issue":"8051","key":"10.1016\/j.media.2026.104196_b34","doi-asserted-by":"crossref","first-page":"769","DOI":"10.1038\/s41586-024-08378-w","article-title":"A vision\u2013language foundation model for precision oncology","volume":"638","author":"Xiang","year":"2025","journal-title":"Nature"},{"key":"10.1016\/j.media.2026.104196_b35","series-title":"Lingshu: A generalist foundation model for unified multimodal medical understanding and reasoning","author":"Xu","year":"2025"},{"issue":"8015","key":"10.1016\/j.media.2026.104196_b36","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1038\/s41586-024-07441-w","article-title":"A whole-slide foundation model for digital pathology from real-world data","volume":"630","author":"Xu","year":"2024","journal-title":"Nature"},{"key":"10.1016\/j.media.2026.104196_b37","series-title":"Data-centric foundation models in computational healthcare: A survey","author":"Zhang","year":"2024"},{"key":"10.1016\/j.media.2026.104196_b38","series-title":"Pmc-vqa: Visual instruction tuning for medical visual question answering","author":"Zhang","year":"2023"},{"key":"10.1016\/j.media.2026.104196_b39","series-title":"Patho-R1: A multimodal reinforcement learning-based pathology expert reasoner","author":"Zhang","year":"2025"},{"key":"10.1016\/j.media.2026.104196_b40","series-title":"Internvl3: Exploring advanced training and test-time recipes for open-source multimodal models","author":"Zhu","year":"2025"}],"container-title":["Medical Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841526002653?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1361841526002653?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T06:53:23Z","timestamp":1785826403000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1361841526002653"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":40,"alternative-id":["S1361841526002653"],"URL":"https:\/\/doi.org\/10.1016\/j.media.2026.104196","relation":{},"ISSN":["1361-8415"],"issn-type":[{"value":"1361-8415","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"OmniPathoVQA: Benchmarking pathology vision\u2013language models with Encyclopedia-scale knowledge","name":"articletitle","label":"Article Title"},{"value":"Medical Image Analysis","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.media.2026.104196","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104196"}}