{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T17:41:55Z","timestamp":1784310115554,"version":"3.55.0"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031439957","type":"print"},{"value":"9783031439964","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-43996-4_27","type":"book-chapter","created":{"date-parts":[[2023,9,30]],"date-time":"2023-09-30T23:07:48Z","timestamp":1696115268000},"page":"281-290","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":41,"title":["SurgicalGPT: End-to-End Language-Vision GPT for\u00a0Visual Question Answering in\u00a0Surgery"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0103-1234","authenticated-orcid":false,"given":"Lalithkumar","family":"Seenivasan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7162-2822","authenticated-orcid":false,"given":"Mobarakol","family":"Islam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2284-703X","authenticated-orcid":false,"given":"Gokul","family":"Kannan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6488-1551","authenticated-orcid":false,"given":"Hongliang","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,10,1]]},"reference":[{"issue":"3","key":"27_CR1","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1109\/38.55152","volume":"10","author":"L Adams","year":"1990","unstructured":"Adams, L., et al.: Computer-assisted surgery. IEEE Comput. Graphics Appl. 10(3), 43\u201351 (1990)","journal-title":"IEEE Comput. Graphics Appl."},{"key":"27_CR2","unstructured":"Allan, M., et al.: 2018 robotic scene segmentation challenge. arXiv preprint arXiv:2001.11190 (2020)"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Bates, D.W., Gawande, A.A.: Error in medicine: what have we learned? (2000)","DOI":"10.1007\/978-1-349-15068-7_16"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Ben-Younes, H., Cadene, R., Cord, M., Thome, N.: Mutan: Multimodal tucker fusion for visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2612\u20132620 (2017)","DOI":"10.1109\/ICCV.2017.285"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Ben-Younes, H., Cadene, R., Thome, N., Cord, M.: Block bilinear superdiagonal fusion for visual question answering and visual relationship detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8102\u20138109 (2019)","DOI":"10.1609\/aaai.v33i01.33018102"},{"key":"27_CR6","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: Advance in Neural Information Processing System, vol. 33, pp. 1877\u20131901 (2020)"},{"key":"27_CR7","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"Guo, J., et al.: From images to textual prompts: zero-shot VQA with frozen large language models. arXiv preprint arXiv:2212.10846 (2022)","DOI":"10.1109\/CVPR52729.2023.01046"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"27_CR10","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1007\/s10055-020-00469-z","volume":"25","author":"M Hong","year":"2021","unstructured":"Hong, M., Rozenblit, J.W., Hamilton, A.J.: Simulation-based surgical training systems in laparoscopic surgery: a current review. Virtual Reality 25, 491\u2013510 (2021)","journal-title":"Virtual Reality"},{"issue":"3","key":"27_CR11","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1046\/j.1365-2923.2003.01440.x","volume":"37","author":"R Kneebone","year":"2003","unstructured":"Kneebone, R.: Simulation in surgical training: educational issues and practical implications. Med. Educ. 37(3), 267\u2013277 (2003)","journal-title":"Med. Educ."},{"key":"27_CR12","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)"},{"key":"27_CR13","unstructured":"Liu, X., et al.: GPT understands, too. arXiv preprint arXiv:2103.10385 (2021)"},{"key":"27_CR14","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"27_CR15","unstructured":"Peng, B., Li, C., Li, J., Shayandeh, S., Liden, L., Gao, J.: SOLOIST: few-shot task-oriented dialog with a single pretrained auto-regressive model. arXiv preprint arXiv:2005.05298 3 (2020)"},{"issue":"6","key":"27_CR16","doi-asserted-by":"publisher","first-page":"508","DOI":"10.1016\/S0002-9610(98)00087-7","volume":"175","author":"DA Rogers","year":"1998","unstructured":"Rogers, D.A., Yeh, K.A., Howdieshell, T.R.: Computer-assisted learning versus a lecture and feedback seminar for teaching a basic surgical technical skill. Am. J. Surg. 175(6), 508\u2013510 (1998)","journal-title":"Am. J. Surg."},{"issue":"12","key":"27_CR17","doi-asserted-by":"publisher","first-page":"2120","DOI":"10.1111\/j.1742-1241.2007.01435.x","volume":"61","author":"S Sarker","year":"2007","unstructured":"Sarker, S., Patel, B.: Simulation and surgical training. Int. J. Clin. Pract. 61(12), 2120\u20132125 (2007)","journal-title":"Int. J. Clin. Pract."},{"key":"27_CR18","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/978-3-031-16449-1_4","volume-title":"Medical Image Computing and Computer Assisted Intervention-MICCAI 2022","author":"L Seenivasan","year":"2022","unstructured":"Seenivasan, L., Islam, M., Krishna, A.K., Ren, H.: Surgical-VQA: Visual question answering in surgical scenes using transformer. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds.) Medical Image Computing and Computer Assisted Intervention-MICCAI 2022. LNCS, vol. 13437, pp. 33\u201343. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-16449-1_4"},{"issue":"1","key":"27_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-021-98390-1","volume":"11","author":"D Sharma","year":"2021","unstructured":"Sharma, D., Purushotham, S., Reddy, C.K.: MedFuseNet: an attention-based multimodal deep learning model for visual question answering in the medical domain. Sci. Rep. 11(1), 1\u201318 (2021)","journal-title":"Sci. Rep."},{"key":"27_CR20","unstructured":"Thoppilan, R., et al.: LAMDA: language models for dialog applications. arXiv preprint arXiv:2201.08239 (2022)"},{"issue":"1","key":"27_CR21","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1109\/TMI.2016.2593957","volume":"36","author":"AP Twinanda","year":"2016","unstructured":"Twinanda, A.P., Shehata, S., Mutter, D., Marescaux, J., De Mathelin, M., Padoy, N.: Endonet: a deep architecture for recognition tasks on laparoscopic videos. IEEE Trans. Med. Imaging 36(1), 86\u201397 (2016)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"27_CR22","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"442","DOI":"10.1007\/978-3-031-16449-1_42","volume-title":"Medical Image Computing and Computer Assisted Intervention-MICCAI 2022","author":"N Valderrama","year":"2022","unstructured":"Valderrama, N., et al.: Towards holistic surgical scene understanding. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds.) Medical Image Computing and Computer Assisted Intervention-MICCAI 2022. LNCS, vol. 13437, pp. 442\u2013452. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-16449-1_42"},{"key":"27_CR23","doi-asserted-by":"crossref","unstructured":"Wang, S., Zhao, Z., Ouyang, X., Wang, Q., Shen, D.: ChatCAD: interactive computer-aided diagnosis on medical image using large language models. arXiv preprint arXiv:2302.07257 (2023)","DOI":"10.1038\/s44172-024-00271-8"},{"key":"27_CR24","doi-asserted-by":"crossref","unstructured":"Yu, Z., Yu, J., Fan, J., Tao, D.: Multi-modal factorized bilinear pooling with co-attention learning for visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1821\u20131830 (2017)","DOI":"10.1109\/ICCV.2017.202"},{"issue":"12","key":"27_CR25","doi-asserted-by":"publisher","first-page":"5947","DOI":"10.1109\/TNNLS.2018.2817340","volume":"29","author":"Z Yu","year":"2018","unstructured":"Yu, Z., Yu, J., Xiang, C., Fan, J., Tao, D.: Beyond bilinear: generalized multimodal factorized high-order pooling for visual question answering. IEEE Trans. Neural Netw. Learn. Syst. 29(12), 5947\u20135959 (2018)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-43996-4_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:16:22Z","timestamp":1730229382000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-43996-4_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031439957","9783031439964"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-43996-4_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"1 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MICCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Medical Image Computing and Computer-Assisted Intervention","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vancouver, BC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2023\/en\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2250","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"730","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"32% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}