{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T14:51:02Z","timestamp":1781016662515,"version":"3.54.1"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032080080","type":"print"},{"value":"9783032080097","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-08009-7_6","type":"book-chapter","created":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T04:37:01Z","timestamp":1760157421000},"page":"53-63","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Kvasir-VQA-x1:A Multimodal Dataset for\u00a0Medical Reasoning and\u00a0Robust MedVQA in\u00a0Gastrointestinal Endoscopy"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9232-2661","authenticated-orcid":false,"given":"Sushant","family":"Gautam","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3153-2064","authenticated-orcid":false,"given":"Michael","family":"Riegler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2073-7029","authenticated-orcid":false,"given":"P\u00e5l","family":"Halvorsen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,12]]},"reference":[{"key":"6_CR1","doi-asserted-by":"publisher","unstructured":"Alayrac, J.B et\u00a0al.: Flamingo: a Visual Language Model for Few-Shot Learning. arXiv (Apr 2022). https:\/\/doi.org\/10.48550\/arXiv.2204.14198","DOI":"10.48550\/arXiv.2204.14198"},{"key":"6_CR2","doi-asserted-by":"publisher","unstructured":"Ali, S., Zhou, F., Bailey, A., Braden, B., East, J., Lu, X., Rittscher, J.: A deep learning framework for quality assessment and restoration in video endoscopy. arXiv (Apr 2019). https:\/\/doi.org\/10.1016\/j.media.2020.101900","DOI":"10.1016\/j.media.2020.101900"},{"key":"6_CR3","unstructured":"Bai, S., et al.: Qwen2.5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"issue":"3","key":"6_CR4","doi-asserted-by":"publisher","first-page":"380","DOI":"10.3390\/bioengineering10030380","volume":"10","author":"Y Bazi","year":"2023","unstructured":"Bazi, Y., Rahhal, M.M.A., Bashmal, L., Zuair, M.: Vision-language model for visual question answering in medical imagery. Bioengineering 10(3), 380 (2023). https:\/\/doi.org\/10.3390\/bioengineering10030380. Mar","journal-title":"Bioengineering"},{"issue":"283","key":"6_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41597-020-00622-y","volume":"7","author":"H Borgli","year":"2020","unstructured":"Borgli, H., et al.: HyperKvasir, a comprehensive multi-class image and video dataset for gastrointestinal endoscopy. Sci. Data 7(283), 1\u201314 (2020). https:\/\/doi.org\/10.1038\/s41597-020-00622-y. Aug","journal-title":"Sci. Data"},{"key":"6_CR6","doi-asserted-by":"publisher","unstructured":"Buslaev, A., Parinov, A., Khvedchenya, E., Iglovikov, V.I., Kalinin, A.A.: Albumentations: fast and flexible image augmentations. arXiv (Sep 2018). https:\/\/doi.org\/10.3390\/info11020125","DOI":"10.3390\/info11020125"},{"key":"6_CR7","doi-asserted-by":"publisher","unstructured":"Chen, X., Lai, Z., Ruan, K., Chen, S., Liu, J., Liu, Z.: R-LLaVA: improving Med-VQA Understanding through Visual Region of Interest. arXiv (Oct 2024). https:\/\/doi.org\/10.48550\/arXiv.2410.20327","DOI":"10.48550\/arXiv.2410.20327"},{"issue":"6","key":"6_CR8","doi-asserted-by":"publisher","first-page":"2983","DOI":"10.3390\/app15062983","volume":"15","author":"W Dong","year":"2025","unstructured":"Dong, W., Shen, S., Han, Y., Tan, T., Wu, J., Xu, H.: Generative Models in Medical Visual Question Answering: A Survey. Appl. Sci. 15(6), 2983 (2025). https:\/\/doi.org\/10.3390\/app15062983. Mar","journal-title":"Appl. Sci."},{"key":"6_CR9","doi-asserted-by":"publisher","unstructured":"Gautam, S., Stor s, A., Midoglu, C., Hicks, S.A., Thambawita, V., Halvorsen, P., Riegler, M.A.: Kvasir-vqa: a text-image pair gi tract dataset. In: Proceedings of the First International Workshop on Vision-Language Models for Biomedical Applications (VLM4Bio 2024), 10 pages. ACM (2024). https:\/\/doi.org\/10.1145\/3689096.3689458","DOI":"10.1145\/3689096.3689458"},{"key":"6_CR10","unstructured":"Google: Medgemma hugging face (May 2025). https:\/\/huggingface.co\/collections\/google\/medgemma-release-680aade845f90bec6a3f60c4, [Accessed 29 May 2025]"},{"key":"6_CR11","doi-asserted-by":"publisher","unstructured":"Gu, T., Yang, K., Liu, D., Cai, W.: LaPA: latent Prompt Assist Model For Medical Visual Question Answering. arXiv (Apr 2024). https:\/\/doi.org\/10.48550\/arXiv.2404.13039","DOI":"10.48550\/arXiv.2404.13039"},{"key":"6_CR12","doi-asserted-by":"publisher","first-page":"1430984","DOI":"10.3389\/frai.2024.1430984","volume":"7","author":"I Hartsock","year":"2024","unstructured":"Hartsock, I., Rasool, G.: Vision-language models for medical report generation and visual question answering: a review. Front. Artif. Intell. 7, 1430984 (2024). https:\/\/doi.org\/10.3389\/frai.2024.1430984. Nov","journal-title":"Front. Artif. Intell."},{"key":"6_CR13","doi-asserted-by":"publisher","unstructured":"Hu, E.J., et al.: LoRA: low-Rank Adaptation of Large Language Models. arXiv (Jun 2021). https:\/\/doi.org\/10.48550\/arXiv.2106.09685","DOI":"10.48550\/arXiv.2106.09685"},{"key":"6_CR14","doi-asserted-by":"publisher","unstructured":"Hu, X., et al.: Expert Knowledge-Aware Image Difference Graph Representation Learning for Difference-Aware Medical Visual Question Answering. arXiv (Jul 2023). https:\/\/doi.org\/10.1145\/3580305.3599819","DOI":"10.1145\/3580305.3599819"},{"key":"6_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"218","DOI":"10.1007\/978-3-030-67835-7_19","volume-title":"MultiMedia Modeling","author":"D Jha","year":"2021","unstructured":"Jha, D., et al.: Kvasir-instrument: diagnostic and therapeutic tool segmentation dataset in gastrointestinal endoscopy. In: Loko\u010d, J., et al. (eds.) MMM 2021. LNCS, vol. 12573, pp. 218\u2013229. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-67835-7_19"},{"issue":"180251","key":"6_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2018.251","volume":"5","author":"JJ Lau","year":"2018","unstructured":"Lau, J.J., Gayen, S., Ben Abacha, A., Demner-Fushman, D.: A dataset of clinically generated visual questions and answers about radiology images. Sci. Data 5(180251), 1\u201310 (2018). https:\/\/doi.org\/10.1038\/sdata.2018.251. Nov","journal-title":"Sci. Data"},{"key":"6_CR17","doi-asserted-by":"publisher","unstructured":"Lavie, A., Agarwal, A.: Meteor: an automatic metric for MT evaluation with high levels of correlation with human judgments. In: DL Hosted proceedings, pp. 228\u2013231. Association for Computational Linguistics (Jun 2007). https:\/\/doi.org\/10.5555\/1626355.1626389","DOI":"10.5555\/1626355.1626389"},{"key":"6_CR18","doi-asserted-by":"publisher","unstructured":"Li, C., et al.: LLaVA-Med: training a Large Language-and-Vision Assistant for Biomedicine in One Day. arXiv (Jun 2023). https:\/\/doi.org\/10.48550\/arXiv.2306.00890","DOI":"10.48550\/arXiv.2306.00890"},{"key":"6_CR19","doi-asserted-by":"publisher","unstructured":"Lian, C., Zhou, H.Y., Yu, Y., Wang, L.: Less Could Be Better: parameter-efficient Fine-tuning Advances Medical Vision Foundation Models. arXiv (Jan 2024). https:\/\/doi.org\/10.48550\/arXiv.2401.12215","DOI":"10.48550\/arXiv.2401.12215"},{"issue":"5","key":"6_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2024.103805","volume":"61","author":"X Liang","year":"2024","unstructured":"Liang, X., et al.: Candidate-Heuristic In-Context Learning: A new framework for enhancing medical visual question answering with LLMs. Inform. Process. Manag. 61(5), 103805 (2024). https:\/\/doi.org\/10.1016\/j.ipm.2024.103805. Sep","journal-title":"Inform. Process. Manag."},{"key":"6_CR21","unstructured":"Lin, C.Y.: Rouge: A package for automatic evaluation of summaries. In: Text summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"6_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2023.102611","volume":"143","author":"Z Lin","year":"2023","unstructured":"Lin, Z., et al.: Medical visual question answering: A survey. Artif. Intell. Med. 143, 102611 (2023). https:\/\/doi.org\/10.1016\/j.artmed.2023.102611. Sep","journal-title":"Artif. Intell. Med."},{"key":"6_CR23","doi-asserted-by":"publisher","unstructured":"Liu, B., Zhan, L.M., Xu, L., Ma, L., Yang, Y., Wu, X.M.: Slake: a semantically-labeled knowledge-enhanced dataset for medical visual question answering. In: IEEE 18th International Symposium on Biomedical Imaging (ISBI), pp. 13\u201316. IEEE (2021). https:\/\/doi.org\/10.1109\/ISBI48211.2021.9434010","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"6_CR24","doi-asserted-by":"publisher","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual Instruction Tuning. arXiv (Apr 2023). https:\/\/doi.org\/10.48550\/arXiv.2304.08485","DOI":"10.48550\/arXiv.2304.08485"},{"key":"6_CR25","unstructured":"Mangrulkar, S., Gugger, S., Debut, L., Belkada, Y., Paul, S., Bossan, B.: Peft: State-of-the-art parameter-efficient fine-tuning methods (2022). https:\/\/github.com\/huggingface\/peft"},{"key":"6_CR26","doi-asserted-by":"publisher","unstructured":"Moor, M., et al.: Med-Flamingo: a Multimodal Medical Few-shot Learner. arXiv (Jul 2023). https:\/\/doi.org\/10.48550\/arXiv.2307.15189","DOI":"10.48550\/arXiv.2307.15189"},{"key":"6_CR27","doi-asserted-by":"publisher","unstructured":"OpenAI, Achiam, J., et\u00a0al.: GPT-4 Technical Report. arXiv (Mar 2023). https:\/\/doi.org\/10.48550\/arXiv.2303.08774","DOI":"10.48550\/arXiv.2303.08774"},{"key":"6_CR28","doi-asserted-by":"publisher","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: DL Hosted Proceedings, pp. 311\u2013318. Association for Computational Linguistics (Jul 2002). https:\/\/doi.org\/10.3115\/1073083.1073135","DOI":"10.3115\/1073083.1073135"},{"key":"6_CR29","doi-asserted-by":"publisher","unstructured":"Popovi\u0107, M.: chrF: character n-gram F-score for automatic MT evaluation. ACL Anthol., 392\u2013395 (Sep 2015). https:\/\/doi.org\/10.18653\/v1\/W15-3049","DOI":"10.18653\/v1\/W15-3049"},{"key":"6_CR30","doi-asserted-by":"publisher","unstructured":"Rajbhandari, S., Rasley, J., Ruwase, O., He, Y.: ZeRO: Memory Optimizations Toward Training Trillion Parameter Models. arXiv (Oct 2019). https:\/\/doi.org\/10.48550\/arXiv.1910.02054","DOI":"10.48550\/arXiv.1910.02054"},{"key":"6_CR31","doi-asserted-by":"publisher","unstructured":"Safavi-Naini, S.A.A., et\u00a0al.: Vision-Language and Large Language Model Performance in Gastroenterology: GPT, Claude, Llama, Phi, Mistral, Gemma, and Quantized Models. arXiv (Aug 2024). https:\/\/doi.org\/10.48550\/arXiv.2409.00084","DOI":"10.48550\/arXiv.2409.00084"},{"key":"6_CR32","doi-asserted-by":"publisher","unstructured":"Sellam, T., Das, D., Parikh, A.P.: BLEURT: Learning Robust Metrics for Text Generation. arXiv (Apr 2020). https:\/\/doi.org\/10.48550\/arXiv.2004.04696","DOI":"10.48550\/arXiv.2004.04696"},{"key":"6_CR33","unstructured":"Team, Q.: Qwen3 technical report (2025). https:\/\/arxiv.org\/abs\/2505.09388"},{"key":"6_CR34","doi-asserted-by":"publisher","unstructured":"Wang, X., et\u00a0al.: ChatGPT: promise and challenges for deployment in low- and middle-income countries. Lancet Regional Health \u2013 Western Pacific 41 (2023). https:\/\/doi.org\/10.1016\/j.lanwpc.2023.100905","DOI":"10.1016\/j.lanwpc.2023.100905"},{"issue":"160018","key":"6_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2016.18","volume":"3","author":"MD Wilkinson","year":"2016","unstructured":"Wilkinson, M.D., et al.: The FAIR Guiding Principles for scientific data management and stewardship. Sci. Data 3(160018), 1\u20139 (2016). https:\/\/doi.org\/10.1038\/sdata.2016.18. Mar","journal-title":"Sci. Data"},{"key":"6_CR36","unstructured":"Wolf, T., et al.: Transformers: State-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38\u201345. Association for Computational Linguistics, Online (Oct 2020). https:\/\/www.aclweb.org\/anthology\/2020.emnlp-demos.6"},{"key":"6_CR37","doi-asserted-by":"publisher","unstructured":"Xu, L., Xie, H., Qin, S.Z.J., Tao, X., Wang, F.L.: Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment. arXiv (Dec 2023). https:\/\/doi.org\/10.48550\/arXiv.2312.12148","DOI":"10.48550\/arXiv.2312.12148"},{"key":"6_CR38","doi-asserted-by":"publisher","unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K.Q., Artzi, Y.: BERTScore: Evaluating Text Generation with BERT. arXiv (Apr 2019). https:\/\/doi.org\/10.48550\/arXiv.1904.09675","DOI":"10.48550\/arXiv.1904.09675"},{"key":"6_CR39","doi-asserted-by":"publisher","unstructured":"Zhang, X., et al.: PMC-VQA: visual Instruction Tuning for Medical Visual Question Answering. arXiv (May 2023). https:\/\/doi.org\/10.48550\/arXiv.2305.10415","DOI":"10.48550\/arXiv.2305.10415"},{"key":"6_CR40","unstructured":"Zhao, Y., et al.: Swift: a scalable lightweight infrastructure for fine-tuning (2024). https:\/\/arxiv.org\/abs\/2408.05517"}],"container-title":["Lecture Notes in Computer Science","Data Engineering in Medical Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-08009-7_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T04:37:07Z","timestamp":1760157427000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-08009-7_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"ISBN":["9783032080080","9783032080097"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-08009-7_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,12]]},"assertion":[{"value":"12 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DEMI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"MICCAI Workshop on Data Engineering in Medical Imaging","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"demi2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}