{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T10:01:58Z","timestamp":1789984918407,"version":"4.0.1"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032380586","type":"print"},{"value":"9783032380593","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T00:00:00Z","timestamp":1790035200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T00:00:00Z","timestamp":1790035200000},"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":[[2027]]},"DOI":"10.1007\/978-3-032-38059-3_43","type":"book-chapter","created":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T09:12:30Z","timestamp":1789981950000},"page":"450-459","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Proto-CAP: Prototype Memory Fusion and\u00a0Curriculum-Adaptive Loss for\u00a0Pediatric Myopia Visual Question Answering"],"prefix":"10.1007","author":[{"given":"Xu","family":"Yan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanlin","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zixun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingtao","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruihua","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,22]]},"reference":[{"key":"43_CR1","doi-asserted-by":"crossref","unstructured":"Chen, Q., Bian, M., Xu, H.: MMQL: multi-question learning for medical visual question answering. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 480\u2013489. Springer (2024)","DOI":"10.1007\/978-3-031-72086-4_45"},{"key":"43_CR2","unstructured":"Eslami, S., De Melo, G., Meinel, C.: Does clip benefit visual question answering in the medical domain as much as it does in the general domain? arXiv preprint arXiv:2112.13906 (2021)"},{"key":"43_CR3","doi-asserted-by":"crossref","unstructured":"Gong, H., Chen, G., Liu, S., Yu, Y., Li, G.: Cross-modal self-attention with multi-task pre-training for medical visual question answering. In: Proceedings of the 2021 International Conference on Multimedia Retrieval, pp. 456\u2013460 (2021)","DOI":"10.1145\/3460426.3463584"},{"key":"43_CR4","doi-asserted-by":"crossref","unstructured":"Holden, B.A., et al.: Global prevalence of myopia and high myopia and temporal trends from 2000 through 2050. Ophthalmology 123(5), 1036\u20131042 (2016)","DOI":"10.1016\/j.ophtha.2016.01.006"},{"key":"43_CR5","doi-asserted-by":"crossref","unstructured":"Holland, R., et al.: Specialized curricula for training vision language models in retinal image analysis. NPJ Digit. Med. 8(1), 532 (2025)","DOI":"10.1038\/s41746-025-01893-8"},{"key":"43_CR6","doi-asserted-by":"crossref","unstructured":"Kenton, J.D.M.W.C., Toutanova, L.K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT, vol. 1, pp. 4171\u20134186, Minneapolis, Minnesota (2019)","DOI":"10.18653\/v1\/N19-1423"},{"issue":"1","key":"43_CR7","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(1), 1\u201310 (2018)","journal-title":"Sci. Data"},{"key":"43_CR8","unstructured":"Leng, Z., et al.: Polyloss: a polynomial expansion perspective of classification loss functions. arXiv preprint arXiv:2204.12511 (2022)"},{"key":"43_CR9","doi-asserted-by":"crossref","unstructured":"Li, P., Liu, G., He, J., Zhao, Z., Zhong, S.: Masked vision and language pre-training with unimodal and multimodal contrastive losses for medical visual question answering. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 374\u2013383. Springer (2023)","DOI":"10.1007\/978-3-031-43907-0_36"},{"key":"43_CR10","doi-asserted-by":"crossref","unstructured":"Li, P., Liu, G., Tan, L., Liao, J., Zhong, S.: Self-supervised vision-language pretraining for medial visual question answering. In: 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI), pp.\u00a01\u20135. IEEE (2023)","DOI":"10.1109\/ISBI53787.2023.10230743"},{"key":"43_CR11","doi-asserted-by":"crossref","unstructured":"Lin, Z., et al.: Medical visual question answering: a survey. Artif. Intell. Med. 143, 102611 (2023)","DOI":"10.1016\/j.artmed.2023.102611"},{"key":"43_CR12","doi-asserted-by":"crossref","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: 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), pp. 1650\u20131654. IEEE (2021)","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"43_CR13","doi-asserted-by":"crossref","unstructured":"Liu, L., Su, X.: How well apply multimodal MIXUP and simple MLPs backbone to medical visual question answering? In: 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 2648\u20132655. IEEE (2022)","DOI":"10.1109\/BIBM55620.2022.9995347"},{"key":"43_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":"43_CR15","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arxiv:1711.05101 (2017)"},{"key":"43_CR16","doi-asserted-by":"crossref","unstructured":"Seenivasan, L., Islam, M., Krishna, A.K., Ren, H.: Surgical-VQA: visual question answering in surgical scenes using transformer. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 33\u201343. Springer (2022)","DOI":"10.1007\/978-3-031-16449-1_4"},{"key":"43_CR17","unstructured":"Shu, J., et al.: Meta-weight-net: learning an explicit mapping for sample weighting. Adv. Neural. Inf. Process. Syst. 32 (2019)"},{"key":"43_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101693","volume":"63","author":"N Tajbakhsh","year":"2020","unstructured":"Tajbakhsh, N., Jeyaseelan, L., Li, Q., Chiang, J.N., Wu, Z., Ding, X.: Embracing imperfect datasets: a review of deep learning solutions for medical image segmentation. Med. Image Anal. 63, 101693 (2020)","journal-title":"Med. Image Anal."},{"key":"43_CR19","doi-asserted-by":"crossref","unstructured":"Tascon-Morales, S., M\u00e1rquez-Neila, P., Sznitman, R.: Consistency-preserving visual question answering in medical imaging. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 386\u2013395. Springer (2022)","DOI":"10.1007\/978-3-031-16452-1_37"},{"key":"43_CR20","doi-asserted-by":"crossref","unstructured":"Tascon-Morales, S., M\u00e1rquez-Neila, P., Sznitman, R.: Localized questions in medical visual question answering. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 361\u2013370. Springer (2023)","DOI":"10.1007\/978-3-031-43895-0_34"},{"key":"43_CR21","doi-asserted-by":"crossref","unstructured":"Ting, D.S., et al.: Deep learning in ophthalmology: the technical and clinical considerations. Prog. Retin. Eye Res. 72, 100759 (2019)","DOI":"10.1016\/j.preteyeres.2019.04.003"},{"key":"43_CR22","unstructured":"Xu, P., et al.: Benchmarking large multimodal models for ophthalmic visual question answering with ophthalwechat. arXiv preprint arXiv:2505.19624 (2025)"},{"key":"43_CR23","doi-asserted-by":"crossref","unstructured":"Zhan, L.M., Liu, B., Fan, L., Chen, J., Wu, X.M.: Medical visual question answering via conditional reasoning. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 2345\u20132354 (2020)","DOI":"10.1145\/3394171.3413761"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-38059-3_43","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T09:12:47Z","timestamp":1789981967000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-38059-3_43"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,22]]},"ISBN":["9783032380586","9783032380593"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-38059-3_43","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,22]]},"assertion":[{"value":"22 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","label":"Disclosure of Interests","group":{"name":"EthicsHeading","label":"Ethics"}},{"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":"Strasbourg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 October 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2026\/en\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}