{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:19:34Z","timestamp":1775229574839,"version":"3.50.1"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031439865","type":"print"},{"value":"9783031439872","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\/978-3-031-43987-2_35","type":"book-chapter","created":{"date-parts":[[2023,9,30]],"date-time":"2023-09-30T23:07:48Z","timestamp":1696115268000},"page":"358-367","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Transformer-Based End-to-End Classification of\u00a0Variable-Length Volumetric Data"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7391-1612","authenticated-orcid":false,"given":"Marzieh","family":"Oghbaie","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9687-528X","authenticated-orcid":false,"given":"Teresa","family":"Ara\u00fajo","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6753-5048","authenticated-orcid":false,"given":"Taha","family":"Emre","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7788-7311","authenticated-orcid":false,"given":"Ursula","family":"Schmidt-Erfurth","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9168-0894","authenticated-orcid":false,"given":"Hrvoje","family":"Bogunovi\u0107","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,10,1]]},"reference":[{"key":"35_CR1","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Schmid, C.: Vivit: a video vision transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6836\u20136846 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"35_CR2","doi-asserted-by":"crossref","unstructured":"Beyer, L., et al.: Flexivit: one model for all patch sizes. arXiv preprint arXiv:2212.08013 (2022)","DOI":"10.1109\/CVPR52729.2023.01393"},{"issue":"5","key":"35_CR3","doi-asserted-by":"publisher","first-page":"710","DOI":"10.1109\/TIP.2004.826093","volume":"13","author":"T Blu","year":"2004","unstructured":"Blu, T., Th\u00e9venaz, P., Unser, M.: Linear interpolation revitalized. IEEE Trans. Image Process. 13(5), 710\u2013719 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"35_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/978-3-319-54184-6_6","volume-title":"Computer Vision \u2013 ACCV 2016","author":"JS Chung","year":"2017","unstructured":"Chung, J.S., Zisserman, A.: Lip reading in the wild. In: Lai, S.-H., Lepetit, V., Nishino, K., Sato, Y. (eds.) ACCV 2016. LNCS, vol. 10112, pp. 87\u2013103. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-54184-6_6"},{"key":"35_CR5","doi-asserted-by":"publisher","first-page":"1025","DOI":"10.1109\/LSP.2020.3000933","volume":"27","author":"V Das","year":"2020","unstructured":"Das, V., Prabhakararao, E., Dandapat, S., Bora, P.K.: B-scan attentive CNN for the classification of retinal optical coherence tomography volumes. IEEE Signal Process. Lett. 27, 1025\u20131029 (2020)","journal-title":"IEEE Signal Process. Lett."},{"issue":"9","key":"35_CR6","doi-asserted-by":"publisher","first-page":"1342","DOI":"10.1038\/s41591-018-0107-6","volume":"24","author":"J De Fauw","year":"2018","unstructured":"De Fauw, J., et al.: Clinically applicable deep learning for diagnosis and referral in retinal disease. Nat. Med. 24(9), 1342\u20131350 (2018)","journal-title":"Nat. Med."},{"key":"35_CR7","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"35_CR8","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"issue":"11","key":"35_CR9","doi-asserted-by":"publisher","first-page":"116011","DOI":"10.1117\/1.JBO.22.11.116011","volume":"22","author":"L Fang","year":"2017","unstructured":"Fang, L., Wang, C., Li, S., Yan, J., Chen, X., Rabbani, H.: Automatic classification of retinal three-dimensional optical coherence tomography images using principal component analysis network with composite kernels. J. Biomed. Opt. 22(11), 116011\u2013116011 (2017)","journal-title":"J. Biomed. Opt."},{"key":"35_CR10","unstructured":"He, K., et al.: Transformers in medical image analysis: a review. Intell. Med. (2022)"},{"key":"35_CR11","doi-asserted-by":"crossref","unstructured":"Howard, J.P., et al.: Improving ultrasound video classification: an evaluation of novel deep learning methods in echocardiography. J. Med. Artif. Intell. 3 (2020)","DOI":"10.21037\/jmai.2019.10.03"},{"key":"35_CR12","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"35_CR13","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1007\/978-3-031-16443-9_16","volume-title":"Medical Image Computing and Computer Assisted Intervention-MICCAI 2022","author":"H Peiris","year":"2022","unstructured":"Peiris, H., Hayat, M., Chen, Z., Egan, G., Harandi, M.: A robust volumetric transformer for accurate 3D tumor segmentation. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds.) MICCAI 2022. LNCS, vol. 13435, pp. 162\u2013172. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-16443-9_16"},{"key":"35_CR14","doi-asserted-by":"publisher","first-page":"102608","DOI":"10.1016\/j.media.2022.102608","volume":"82","author":"C Playout","year":"2022","unstructured":"Playout, C., Duval, R., Boucher, M.C., Cheriet, F.: Focused attention in transformers for interpretable classification of retinal images. Med. Image Anal. 82, 102608 (2022)","journal-title":"Med. Image Anal."},{"key":"35_CR15","unstructured":"Prabhushankar, M., Kokilepersaud, K., Logan, Y.Y., Corona, S.T., AlRegib, G., Wykoff, C.: Olives dataset: Ophthalmic labels for investigating visual eye semantics. arXiv preprint arXiv:2209.11195 (2022)"},{"key":"35_CR16","doi-asserted-by":"publisher","first-page":"103327","DOI":"10.1016\/j.compbiomed.2019.103327","volume":"111","author":"J Qiu","year":"2019","unstructured":"Qiu, J., Sun, Y.: Self-supervised iterative refinement learning for macular oct volumetric data classification. Comput. Biol. Med. 111, 103327 (2019)","journal-title":"Comput. Biol. Med."},{"issue":"4","key":"35_CR17","doi-asserted-by":"publisher","first-page":"1024","DOI":"10.1109\/TMI.2017.2780115","volume":"37","author":"R Rasti","year":"2017","unstructured":"Rasti, R., Rabbani, H., Mehridehnavi, A., Hajizadeh, F.: Macular OCT classification using a multi-scale convolutional neural network ensemble. IEEE Trans. Med. Imaging 37(4), 1024\u20131034 (2017)","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"12","key":"35_CR18","doi-asserted-by":"publisher","first-page":"3456","DOI":"10.1109\/JBHI.2020.3000136","volume":"24","author":"D Romo-Bucheli","year":"2020","unstructured":"Romo-Bucheli, D., Erfurth, U.S., Bogunovi\u0107, H.: End-to-end deep learning model for predicting treatment requirements in neovascular AMD from longitudinal retinal OCT imaging. IEEE J. Biomed. Health Inform. 24(12), 3456\u20133465 (2020)","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"35_CR19","doi-asserted-by":"crossref","unstructured":"Semivariogram and semimadogram functions as descriptors for AMD diagnosis on SD-OCT topographic maps using support vector machine. Biomed. Eng. Online 17(1), 1\u201320 (2018)","DOI":"10.1186\/s12938-018-0592-3"},{"key":"35_CR20","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"issue":"18","key":"35_CR21","doi-asserted-by":"publisher","first-page":"5097","DOI":"10.3390\/s20185097","volume":"20","author":"SP Singh","year":"2020","unstructured":"Singh, S.P., Wang, L., Gupta, S., Goli, H., Padmanabhan, P., Guly\u00e1s, B.: 3D deep learning on medical images: a review. Sensors 20(18), 5097 (2020)","journal-title":"Sensors"},{"issue":"9","key":"35_CR22","doi-asserted-by":"publisher","first-page":"096004","DOI":"10.1117\/1.JBO.25.9.096004","volume":"25","author":"Y Sun","year":"2020","unstructured":"Sun, Y., Zhang, H., Yao, X.: Automatic diagnosis of macular diseases from OCT volume based on its two-dimensional feature map and convolutional neural network with attention mechanism. J. Biomed. Opt. 25(9), 096004\u2013096004 (2020)","journal-title":"J. Biomed. Opt."},{"issue":"8","key":"35_CR23","first-page":"2118","volume":"62","author":"C de Vente","year":"2021","unstructured":"de Vente, C., Gonz\u00e1lez-Gonzalo, C., Thee, E.F., van Grinsven, M., Klaver, C.C., S\u00e1nchez, C.I.: Making AI transferable across oct scanners from different vendors. Invest. Ophthalmol. Visual Sci. 62(8), 2118\u20132118 (2021)","journal-title":"Invest. Ophthalmol. Visual Sci."},{"key":"35_CR24","doi-asserted-by":"crossref","unstructured":"Wang, J., Cherian, A., Porikli, F., Gould, S.: Video representation learning using discriminative pooling. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1149\u20131158 (2018)","DOI":"10.1109\/CVPR.2018.00126"},{"key":"35_CR25","doi-asserted-by":"publisher","unstructured":"Wightman, R.: Pytorch image models (2019) https:\/\/doi.org\/10.5281\/zenodo.4414861. https:\/\/github.com\/rwightman\/pytorch-image-models","DOI":"10.5281\/zenodo.4414861"},{"key":"35_CR26","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1007\/978-3-031-16437-8_26","volume-title":"Medical Image Computing and Computer Assisted Intervention-MICCAI 2022","author":"R Windsor","year":"2022","unstructured":"Windsor, R., Jamaludin, A., Kadir, T., Zisserman, A.: Context-aware transformers for spinal cancer detection and radiological grading. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds.) MICCAI 2022. LNCS, vol. 13433, pp. 271\u2013281. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-16437-8_26"},{"issue":"6","key":"35_CR27","doi-asserted-by":"publisher","first-page":"e0233678","DOI":"10.1371\/journal.pone.0233678","volume":"15","author":"E Wulczyn","year":"2020","unstructured":"Wulczyn, E., et al.: Deep learning-based survival prediction for multiple cancer types using histopathology images. PLoS ONE 15(6), e0233678 (2020)","journal-title":"PLoS ONE"},{"key":"35_CR28","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Zheng, L., Kang, G., Li, S., Yang, Y.: Random erasing data augmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 13001\u201313008 (2020)","DOI":"10.1609\/aaai.v34i07.7000"}],"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\/978-3-031-43987-2_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,11]],"date-time":"2024-03-11T15:31:37Z","timestamp":1710171097000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-43987-2_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031439865","9783031439872"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-43987-2_35","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)"}}]}}