{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T16:30:25Z","timestamp":1790785825402,"version":"4.1.0"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T00:00:00Z","timestamp":1779408000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T00:00:00Z","timestamp":1779408000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100006690","name":"Politecnico di Milano","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100006690","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J CARS"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>Video question answering (VideoQA) in the surgical domain aims to enhance intraoperative understanding by enabling AI models to reason over temporally coherent events rather than isolated frames. Current approaches are limited to static image features, and available datasets often lack temporal annotations, ignoring the dynamics critical for accurate procedural interpretation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We propose SurgViVQA, a surgical VideoQA model that extends visual reasoning from static images to dynamic surgical scenes. It uses a Masked Video\u2013Text Encoder to fuse video and question features, capturing temporal cues like motion and tool\u2013tissue interactions, which a fine-tuned LLM then decodes into coherent answers. To evaluate its performance, we curate REAL-Colon-VQA, a colonoscopic video dataset including motion questions and diagnostic attributes, including out-of-template questions with rephrased or semantically altered formulations to evaluate model robustness.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Experimental validation on REAL-Colon-VQA and the public EndoVis18-VQA dataset shows that SurgViVQA outperforms existing image-based VQA benchmark models and remains competitive with a fine-tuned video VLM baseline. In particular, SurgViVQA improves over PitVQA by +9% on REAL-Colon-VQA and +9% on EndoVis18-VQA in Keyword Accuracy, while achieving the strongest overall lexical and semantic generation performance. A perturbation study on the questions further confirms improved generalizability and robustness to variations in question phrasing.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>SurgViVQA and the REAL-Colon-VQA dataset provide a framework for temporally aware understanding in surgical VideoQA, enabling AI models to interpret dynamic procedural contexts.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s11548-026-03695-z","type":"journal-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T14:50:49Z","timestamp":1779461449000},"page":"1369-1377","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["SurgViVQA: temporally grounded video question answering for surgical scene understanding"],"prefix":"10.1007","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1593-4203","authenticated-orcid":false,"given":"Mauro Orazio","family":"Drago","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1365-6661","authenticated-orcid":false,"given":"Luca","family":"Carlini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pelinsu Celebi","family":"Balyemez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dennis","family":"Pierantozzi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chiara","family":"Lena","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7167-1459","authenticated-orcid":false,"given":"Cesare","family":"Hassan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0980-3227","authenticated-orcid":false,"given":"Danail","family":"Stoyanov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8819-2734","authenticated-orcid":false,"given":"Elena De","family":"Momi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1329-4565","authenticated-orcid":false,"given":"Sophia","family":"Bano","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7162-2822","authenticated-orcid":false,"given":"Mobarak I.","family":"Hoque","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,22]]},"reference":[{"issue":"5","key":"3695_CR1","doi-asserted-by":"publisher","first-page":"947","DOI":"10.1210\/endrev\/bnad014","volume":"44","author":"DZ Khan","year":"2023","unstructured":"Khan DZ, Hanrahan JG, Baldeweg SE, Dorward NL, Stoyanov D, Marcus HJ (2023) Current and future advances in surgical therapy for pituitary adenoma. Endocr Rev 44(5):947\u2013959","journal-title":"Endocr Rev"},{"key":"3695_CR2","doi-asserted-by":"crossref","unstructured":"Carlini L, Massimi D, Mori Y, Antonelli G, Rizkala T, Spadaccini M, Lena C, Parasa S, Bisschops R, Von\u00a0Renteln D et al (2025) Large language models for detecting colorectal polyps in endoscopic images. Gut","DOI":"10.1136\/gutjnl-2025-335091"},{"key":"3695_CR3","doi-asserted-by":"crossref","unstructured":"Massimi D, Carlini L, Mori Y, Di\u00a0Stefano L, Antonelli G, Rizkala T, Spadaccini M, Sire R, Alfarone L, Lena C et al (2025) Large language model for interpreting the paris classification of colorectal polyps. Endoscopy Int Open 13(continuous publication)","DOI":"10.1055\/a-2703-0209"},{"key":"3695_CR4","doi-asserted-by":"crossref","unstructured":"Seenivasan L, Islam M, Kannan G, Ren H (2023) Surgicalgpt: end-to-end language-vision gpt for visual question answering in surgery. In: International conference on medical image computing and computer-assisted intervention, Springer, pp 281\u2013290","DOI":"10.1007\/978-3-031-43996-4_27"},{"key":"3695_CR5","unstructured":"Radford A, Wu J, Child R, Luan D, Amodei D, Sutskever I (2019) Language models are unsupervised multitask learners. OpenAI technical report"},{"key":"3695_CR6","doi-asserted-by":"crossref","unstructured":"He R, Khan DZ, Mazomenos EB, Marcus HJ, Stoyanov D, Clarkson MJ, Islam M (2025) Pitvqa++: vector matrix-low-rank adaptation for open-ended visual question answering in pituitary surgery. arXiv preprint arXiv:2502.14149","DOI":"10.1109\/TMI.2026.3681175"},{"key":"3695_CR7","doi-asserted-by":"crossref","unstructured":"Seenivasan L, Islam M, Krishna AK, Ren H (2022) Surgical-vqa: visual question answering in surgical scenes using transformer. In: International conference on medical image computing and computer-assisted intervention, Springer, pp 33\u201343","DOI":"10.1007\/978-3-031-16449-1_4"},{"key":"3695_CR8","doi-asserted-by":"crossref","unstructured":"Gautam S, Stor\u00e5s AM, Midoglu C, Hicks SA, Thambawita V, Halvorsen P, Riegler MA (2024) Kvasir-vqa: a text-image pair gi tract dataset. In: Proceedings of the first international workshop on vision-language models for biomedical applications, pp 3\u201312","DOI":"10.1145\/3689096.3689458"},{"issue":"2","key":"3695_CR9","first-page":"3","volume":"1","author":"EJ Hu","year":"2022","unstructured":"Hu EJ, Shen Y, Wallis P, Allen-Zhu Z, Li Y, Wang S, Wang L, Chen W et al (2022) Lora: low-rank adaptation of large language models. ICLR 1(2):3","journal-title":"ICLR"},{"key":"3695_CR10","unstructured":"Bai J, Bai S, Chu Y, Cui Z, Dang K, Deng X, Fan Y, Ge W, Han Y, Huang F et al (2023) Qwen technical report. arXiv preprint arXiv:2309.16609"},{"key":"3695_CR11","doi-asserted-by":"publisher","first-page":"10078","DOI":"10.52202\/068431-0732","volume":"35","author":"Z Tong","year":"2022","unstructured":"Tong Z, Song Y, Wang J, Wang L (2022) Videomae: masked autoencoders are data-efficient learners for self-supervised video pre-training. Adv Neural Inf Process Syst 35:10078\u201310093","journal-title":"Adv Neural Inf Process Syst"},{"issue":"1","key":"3695_CR12","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1038\/s41597-024-03359-0","volume":"11","author":"C Biffi","year":"2024","unstructured":"Biffi C, Antonelli G, Bernhofer S, Hassan C, Hirata D, Iwatate M, Maieron A, Salvagnini P, Cherubini A (2024) Real-colon: a dataset for developing real-world ai applications in colonoscopy. Sci Data 11(1):539","journal-title":"Sci Data"},{"issue":"7","key":"3695_CR13","doi-asserted-by":"publisher","first-page":"1409","DOI":"10.1007\/s11548-024-03141-y","volume":"19","author":"K Yuan","year":"2024","unstructured":"Yuan K, Kattel M, Lavanchy JL, Navab N, Srivastav V, Padoy N (2024) Advancing surgical vqa with scene graph knowledge. Int J Comput Assist Radiol Surg 19(7):1409\u20131417","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"3695_CR14","doi-asserted-by":"crossref","unstructured":"Pierantozzi D, Carlini L, Drago MO, Lena C, Hassan C, De\u00a0Momi E, Stoyanov D, Bano S, Hoque MI (2025) When to trust the answer: question-aligned semantic neighbour entropy for safer surgical VQA. arXiv preprint arXiv:2511.01458","DOI":"10.1007\/s11548-026-03750-9"},{"key":"3695_CR15","unstructured":"Li J, Li D, Xiong C, Hoi S (2022) Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International conference on machine learning, PMLR, pp 12888\u201312900"},{"key":"3695_CR16","unstructured":"Zhu J, Wang W, Chen Z, Liu Z, Ye S, Gu L, Tian H, Duan Y, Su W, Shao J et al (2025) Internvl3: exploring advanced training and test-time recipes for open-source multimodal models. arXiv preprint arXiv:2504.10479"},{"key":"3695_CR17","unstructured":"Bai S, Chen K, Liu X, Wang J, Ge W, Song S, Dang K, Wang P, Wang S, Tang J, Zhong H, Zhu Y, Yang M, Li Z, Wan J, Wang P, Ding W, Fu Z, Xu Y, Ye J, Zhang X, Xie T, Cheng Z, Zhang H, Yang Z, Xu H, Lin J (2025) Qwen2.5-vl technical report. arXiv preprint arXiv:2502.13923"},{"key":"3695_CR18","unstructured":"Sellergren A, Kazemzadeh S, Jaroensri T, Kiraly A, Traverse M, Kohlberger T, Xu S, Jamil F, Hughes C, Lau C et al (2025) Medgemma technical report. arXiv preprint arXiv:2507.05201"},{"key":"3695_CR19","unstructured":"Zhang B, Li K, Cheng Z, Hu Z, Yuan Y, Chen G, Leng S, Jiang Y, Zhang H, Li X et al (2025) Videollama 3: frontier multimodal foundation models for image and video understanding. arXiv preprint arXiv:2501.13106"},{"key":"3695_CR20","doi-asserted-by":"crossref","unstructured":"Ma Y, Xu G, Sun X, Yan M, Zhang J, Ji R (2022) X-clip: end-to-end multi-grained contrastive learning for video-text retrieval. In: Proceedings of the 30th ACM international conference on multimedia, pp 638\u2013647","DOI":"10.1145\/3503161.3547910"},{"key":"3695_CR21","doi-asserted-by":"crossref","unstructured":"Arnab A, Dehghani M, Heigold G, Sun C, Lu\u010di\u0107 M, Schmid C (2021) Vivit: a video vision transformer. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 6836\u20136846","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"3695_CR22","unstructured":"Bertasius G, Wang H, Torresani L (2021) Is space-time attention all you need for video understanding? In: Icml, vol 2, p 4"},{"key":"3695_CR23","doi-asserted-by":"crossref","unstructured":"Li K, Li X, Wang Y, He Y, Wang Y, Wang L, Qiao Y (2024) Videomamba: state space model for efficient video understanding. In: European conference on computer vision, Springer, pp 237\u2013255","DOI":"10.1007\/978-3-031-73347-5_14"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-026-03695-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-026-03695-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-026-03695-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T13:20:15Z","timestamp":1786108815000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-026-03695-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,22]]},"references-count":23,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["3695"],"URL":"https:\/\/doi.org\/10.1007\/s11548-026-03695-z","relation":{},"ISSN":["1861-6429"],"issn-type":[{"value":"1861-6429","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,22]]},"assertion":[{"value":"5 March 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This article does not contain any new studies with human participants or animals performed by any of the authors. All analyses were conducted on previously published or fully anonymized surgical video datasets, including EndoVis18-VQA and the REAL-Colon dataset from which REAL-Colon-VQA was derived.","order":1,"name":"Ethics","label":"Ethics Approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Authors declare they have no competing financial or non-financial interests directly or indirectly related to the work submitted for publication.","order":2,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"No new data involving human participants were collected for this study. Informed consent was obtained by the original investigators at the time of data acquisition, where applicable; therefore, additional informed consent for this secondary analysis was not required.","order":3,"name":"Ethics","label":"Informed Consent","group":{"name":"EthicsHeading","label":"Declarations"}}]}}