{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T17:18:43Z","timestamp":1787764723346,"version":"build-2784847793"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T00:00:00Z","timestamp":1787702400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T00:00:00Z","timestamp":1787702400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100017052","name":"National Natural Science Foundation of China-Liaoning Joint Fund","doi-asserted-by":"publisher","award":["62101355"],"award-info":[{"award-number":["62101355"]}],"id":[{"id":"10.13039\/100017052","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100017052","name":"National Natural Science Foundation of China-Liaoning Joint Fund","doi-asserted-by":"publisher","award":["62525307"],"award-info":[{"award-number":["62525307"]}],"id":[{"id":"10.13039\/100017052","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Digit Imaging. Inform. med."],"DOI":"10.1007\/s10278-026-02067-y","type":"journal-article","created":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T16:28:41Z","timestamp":1787761721000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["EndoVLM: A Vision-Language Assistant for Gastrointestinal Endoscopy"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5073-3371","authenticated-orcid":false,"given":"Shuai","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengbo","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tiejun","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,26]]},"reference":[{"key":"2067_CR1","doi-asserted-by":"publisher","unstructured":"Wang, S., Zheng, R., Li, J., Zeng, H., Li, L., Chen, R., Sun, K., Han, B., Bray, F., Wei, W., et al.: Global, regional, and national lifetime risks of developing and dying from gastrointestinal cancers in 185 countries: a population-based systematic analysis of GLOBOCAN. The Lancet Gastroenterology & Hepatology 9(3), 229\u2013237 (2024) https:\/\/doi.org\/10.1016\/S2468-1253(23)00366-7","DOI":"10.1016\/S2468-1253(23)00366-7"},{"key":"2067_CR2","doi-asserted-by":"publisher","unstructured":"Chou, C.-K., Lee, K.-H., Karmakar, R., Mukundan, A., Gade, P.C., Gupta, D., Su, C.-C., Chen, T.-H., Ko, C.-Y., Wang, H.-C.: Emulating hyperspectral and narrow-band imaging for deep-learning-driven gastrointestinal disorder detection in wireless capsule endoscopy. Bioengineering 12(9), 953 (2025) https:\/\/doi.org\/10.3390\/bioengineering12090953","DOI":"10.3390\/bioengineering12090953"},{"key":"2067_CR3","doi-asserted-by":"publisher","unstructured":"Berzin, T.M., Parasa, S., Wallace, M.B., Gross, S.A., Repici, A., Sharma, P.: Position statement on priorities for artificial intelligence in GI endoscopy: a report by the ASGE task force. Gastrointestinal Endoscopy 92(4), 951\u2013959 (2020) https:\/\/doi.org\/10.1016\/j.gie.2020.06.035","DOI":"10.1016\/j.gie.2020.06.035"},{"key":"2067_CR4","doi-asserted-by":"publisher","unstructured":"De\u00a0Groof, A.J., Struyvenberg, M.R., van der Putten, J., van der Sommen, F., Fockens, K.N., Curvers, W.L., Zinger, S., Pouw, R.E., Coron, E., Baldaque-Silva, F., et al.: Deep-learning system detects neoplasia in patients with barrett\u2019s esophagus with higher accuracy than endoscopists in a multistep training and validation study with benchmarking. Gastroenterology 158, 915\u2013929 (2020) https:\/\/doi.org\/10.1053\/j.gastro.2019.11.030","DOI":"10.1053\/j.gastro.2019.11.030"},{"key":"2067_CR5","doi-asserted-by":"publisher","unstructured":"Lin, Q., Tan, W., Cai, S., Yan, B., Li, J., Zhong, Y.: Lesion-decoupling-based segmentation with large-scale colon and esophageal datasets for early cancer diagnosis. IEEE Transactions on Neural Networks and Learning Systems 35(8), 11142\u201311156 (2024) https:\/\/doi.org\/10.1109\/TNNLS.2023.3248804","DOI":"10.1109\/TNNLS.2023.3248804"},{"key":"2067_CR6","doi-asserted-by":"publisher","unstructured":"Hartsock, I., Rasool, G.: Vision-language models for medical report generation and visual question answering: a review. Frontiers in Artificial Intelligence 7, 1430984 (2024) https:\/\/doi.org\/10.3389\/frai.2024.1430984","DOI":"10.3389\/frai.2024.1430984"},{"key":"2067_CR7","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"2067_CR8","doi-asserted-by":"publisher","unstructured":"Eslami, S., Meinel, C., De\u00a0Melo, G.: PubMedCLIP: How much does CLIP benefit visual question answering in the medical domain? In: Findings of the Association for Computational Linguistics: EACL 2023, pp. 1181\u20131193 (2023). https:\/\/doi.org\/10.18653\/v1\/2023.findings-eacl.88","DOI":"10.18653\/v1\/2023.findings-eacl.88"},{"key":"2067_CR9","doi-asserted-by":"publisher","unstructured":"Lin, Z., Zhang, D., Tao, Q., Shi, D., Haffari, G., Wu, Q., He, M., Ge, Z.: Medical visual question answering: A survey. Artificial Intelligence in Medicine 143, 102611 (2023) https:\/\/doi.org\/10.1016\/j.artmed.2023.102611","DOI":"10.1016\/j.artmed.2023.102611"},{"key":"2067_CR10","unstructured":"Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F.L., Almeida, D., Altenschmidt, J., Altman, S., Anadkat, S., et al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023) arXiv:2303.08774"},{"key":"2067_CR11","doi-asserted-by":"publisher","unstructured":"Zheng, Y., Zhang, R., Zhang, J., Ye, Y., Luo, Z.: LlamaFactory: Unified efficient fine-tuning of 100+ language models. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), pp. 400\u2013410 (2024). https:\/\/doi.org\/10.18653\/v1\/2024.acl-demos.38","DOI":"10.18653\/v1\/2024.acl-demos.38"},{"key":"2067_CR12","doi-asserted-by":"publisher","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. Advances in Neural Information Processing Systems 36, 34892\u201334916 (2023) https:\/\/doi.org\/10.52202\/075280-1516","DOI":"10.52202\/075280-1516"},{"key":"2067_CR13","unstructured":"Bolton, E., Venigalla, A., Yasunaga, M., Hall, D., Xiong, B., Lee, T., Daneshjou, R., Frankle, J., Liang, P., Carbin, M., et al.: BioMedLM: A 2.7b parameter language model trained on biomedical text. arXiv preprint arXiv:2403.18421 (2024)"},{"key":"2067_CR14","doi-asserted-by":"publisher","unstructured":"Wang, Z., Wu, Z., Agarwal, D., Sun, J.: MedCLIP: Contrastive learning from unpaired medical images and text. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 3876\u20133887 (2022). https:\/\/doi.org\/10.18653\/v1\/2022.emnlp-main.256","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"2067_CR15","unstructured":"Li, L.H., Yatskar, M., Yin, D., Hsieh, C.-J., Chang, K.-W.: VisualBERT: A simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019) arXiv:1908.03557"},{"key":"2067_CR16","unstructured":"Zhang, K., Yu, J., Adhikarla, E., Zhou, R., Yan, Z., Liu, Y., Liu, Z., He, L., Davison, B.D., Li, X., et al.: BiomedGPT: A unified and generalist biomedical generative pre-trained transformer for vision, language, and multimodal tasks. arXiv preprint arXiv:2305.17100 (2023)"},{"key":"2067_CR17","doi-asserted-by":"publisher","unstructured":"Lin, W., Zhao, Z., Zhang, X., Wu, C., Zhang, Y., Wang, Y., Xie, W.: PMC-CLIP: Contrastive language-image pre-training using biomedical documents. In: Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2023, pp. 525\u2013536 (2023). https:\/\/doi.org\/10.1007\/978-3-031-43993-3_51","DOI":"10.1007\/978-3-031-43993-3_51"},{"key":"2067_CR18","doi-asserted-by":"crossref","unstructured":"Hemker, K., Simidjievski, N., Jamnik, M.: HEALNet: Multimodal fusion for heterogeneous biomedical data. arXiv preprint arXiv:2311.09115 (2023)","DOI":"10.52202\/079017-2057"},{"key":"2067_CR19","doi-asserted-by":"publisher","unstructured":"Li, C., Wong, C., Zhang, S., Usuyama, N., Liu, H., Yang, J., Naumann, T., Poon, H., Gao, J.: LLaVA-Med: Training a large language-and-vision assistant for biomedicine in one day. Advances in Neural Information Processing Systems 36, 28541\u201328564 (2023) https:\/\/doi.org\/10.52202\/075280-1240","DOI":"10.52202\/075280-1240"},{"key":"2067_CR20","doi-asserted-by":"publisher","unstructured":"Zhao, Z., Wang, S., Gu, J., Zhu, Y., Mei, L., Zhuang, Z., Cui, Z., Wang, Q., Shen, D.: ChatCAD+: Toward a universal and reliable interactive CAD using LLMs. IEEE Transactions on Medical Imaging 43(11), 3755\u20133766 (2024) https:\/\/doi.org\/10.1109\/TMI.2024.3398350","DOI":"10.1109\/TMI.2024.3398350"},{"key":"2067_CR21","unstructured":"Yang, L., Xu, S., Sellergren, A., Kohlberger, T., Zhou, Y., Ktena, I., Kiraly, A., Ahmed, F., Hormozdiari, F., Jaroensri, T., et al.: Advancing multimodal medical capabilities of gemini. arXiv preprint arXiv:2405.03162 (2024)"},{"key":"2067_CR22","unstructured":"Xu, L., Sun, H., Ni, Z., Li, H., Zhang, S.: Medvilam: A multimodal large language model with advanced generalizability and explainability for medical data understanding and generation. arXiv preprint arXiv:2409.19684 (2024)"},{"key":"2067_CR23","unstructured":"Zhao, T., Gu, Y., Yang, J., Usuyama, N., Lee, H.H., Naumann, T., Gao, J., Crabtree, A., Abel, J., Moung-Wen, C., et al.: Biomedparse: a biomedical foundation model for image parsing of everything everywhere all at once. arXiv preprint arXiv:2405.12971 (2024)"},{"key":"2067_CR24","doi-asserted-by":"publisher","unstructured":"Wu, C., Zhang, X., Zhang, Y., Hui, H., Wang, Y., Xie, W.: Towards generalist foundation model for radiology by leveraging web-scale 2d&3d medical data. Nature Communications 16(1), 7866 (2025) https:\/\/doi.org\/10.1038\/s41467-025-62385-7","DOI":"10.1038\/s41467-025-62385-7"},{"key":"2067_CR25","unstructured":"Chen, Z., Varma, M., Delbrouck, J.-B., Paschali, M., Blankemeier, L., van Veen, D., Valanarasu, J.M.J., Youssef, A., Cohen, J.P., Reis, E.P., et al.: CheXagent: Towards a foundation model for chest X-ray interpretation. In: AAAI 2024 Spring Symposium on Clinical Foundation Models (2024)"},{"key":"2067_CR26","unstructured":"Zhou, J., He, X., Sun, L., Xu, J., Chen, X., Chu, Y., Zhou, L., Liao, X., Zhang, B., Gao, X.: SkinGPT-4: An interactive dermatology diagnostic system with visual large language model. arXiv preprint arXiv:2304.10691 (2023)"},{"key":"2067_CR27","doi-asserted-by":"publisher","unstructured":"Deng, Z., Gao, W., Chen, C., Niu, Z., Gong, Z., Zhang, R., Cao, Z., Li, F., Ma, Z., Wei, W., et al.: OphGLM: An ophthalmology large language-and-vision assistant. Artificial Intelligence in Medicine 157, 103001 (2024) https:\/\/doi.org\/10.1016\/j.artmed.2024.103001","DOI":"10.1016\/j.artmed.2024.103001"},{"key":"2067_CR28","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"2067_CR29","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al.: Learning transferable visual models from natural language supervision. In: Proceedings of the 38th International Conference on Machine Learning, pp. 8748\u20138763 (2021). PMLR"},{"key":"2067_CR30","doi-asserted-by":"publisher","unstructured":"Liu, Z., Mao, H., Wu, C.-Y., Feichtenhofer, C., Darrell, T., Xie, S.: A ConvNet for the 2020s. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11966\u201311976 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01167","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"2067_CR31","doi-asserted-by":"publisher","unstructured":"Sagheer, S.V.M., Meghana, K.H., Ameer, P.M., Parayangat, M., Abbas, M.: Transformers for multi-modal image analysis in healthcare. Computers, Materials & Continua 84(3), 4259\u20134297 (2025) https:\/\/doi.org\/10.32604\/cmc.2025.063726","DOI":"10.32604\/cmc.2025.063726"},{"key":"2067_CR32","doi-asserted-by":"publisher","unstructured":"Xiao, J., Bai, Y., Yuille, A., Zhou, Z.: Delving into masked autoencoders for multi-label thorax disease classification. In: 2023 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 3577\u20133589 (2023). https:\/\/doi.org\/10.1109\/WACV56688.2023.00358","DOI":"10.1109\/WACV56688.2023.00358"},{"key":"2067_CR33","doi-asserted-by":"publisher","unstructured":"Liu, W., Tian, T., Xu, W., Yang, H., Pan, X., Yan, S., Wang, L.: PHTrans: Parallelly aggregating global and local representations for medical image segmentation. In: Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2022, pp. 235\u2013244 (2022). https:\/\/doi.org\/10.1007\/978-3-031-16443-9_23","DOI":"10.1007\/978-3-031-16443-9_23"},{"key":"2067_CR34","doi-asserted-by":"publisher","unstructured":"Madan, S., Lentzen, M., Brandt, J., Rueckert, D., Hofmann-Apitius, M., Fr\u00f6hlich, H.: Transformer models in biomedicine. BMC Medical Informatics and Decision Making 24(1), 214 (2024) https:\/\/doi.org\/10.1186\/s12911-024-02600-5","DOI":"10.1186\/s12911-024-02600-5"},{"key":"2067_CR35","unstructured":"Lin, C.-Y.: ROUGE: A package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"2067_CR36","doi-asserted-by":"publisher","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.-J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002). https:\/\/doi.org\/10.3115\/1073083.1073135","DOI":"10.3115\/1073083.1073135"},{"key":"2067_CR37","unstructured":"Gemma Team, Kamath, A., Ferret, J., Pathak, S., Vieillard, N., Merhej, R., Perrin, S., Matejovicova, T., Ram\u00e9, A., Rivi\u00e8re, M., et al.: Gemma 3 Technical Report. arXiv preprint arXiv:2503.19786 (2025)"},{"key":"2067_CR38","unstructured":"Sellergren, A., Kazemzadeh, S., Jaroensri, T., Kiraly, A., Traverse, M., Kohlberger, T., Xu, S., Jamil, F., Hughes, C., Lau, C., et al.: MedGemma Technical Report. arXiv preprint arXiv:2507.05201 (2025)"},{"key":"2067_CR39","unstructured":"Bai, S., Chen, K., Liu, X., Wang, J., Ge, W., Song, S., Dang, K., Wang, P., Wang, S., Tang, J., et al.: Qwen2.5-VL Technical Report. arXiv preprint arXiv:2502.13923 (2025)"}],"container-title":["Journal of Imaging Informatics in Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10278-026-02067-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10278-026-02067-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10278-026-02067-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T16:28:43Z","timestamp":1787761723000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10278-026-02067-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,26]]},"references-count":39,"alternative-id":["2067"],"URL":"https:\/\/doi.org\/10.1007\/s10278-026-02067-y","relation":{},"ISSN":["2948-2933"],"issn-type":[{"value":"2948-2933","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,26]]},"assertion":[{"value":"9 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 May 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 June 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 August 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This study used publicly available de-identified endoscopic image datasets (Kvasir-VQA and Gastrovision). No human subjects or identifiable patient data were involved. Therefore, formal ethics approval was not required.","order":1,"name":"Ethics","label":"Ethics Approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","label":"Conflict of Interest","group":{"name":"EthicsHeading","label":"Declarations"}}]}}