{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T19:39:53Z","timestamp":1784230793454,"version":"3.55.0"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732928","type":"print"},{"value":"9783031732904","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T00:00:00Z","timestamp":1729641600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T00:00:00Z","timestamp":1729641600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-73290-4_17","type":"book-chapter","created":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T06:02:21Z","timestamp":1729576941000},"page":"169-179","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Identifying Critical Tokens for\u00a0Accurate Predictions in\u00a0Transformer-Based Medical Imaging Models"],"prefix":"10.1007","author":[{"given":"Solha","family":"Kang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joris","family":"Vankerschaver","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Utku","family":"Ozbulak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,23]]},"reference":[{"key":"17_CR1","doi-asserted-by":"crossref","unstructured":"Bai, B., Liang, J., Zhang, G., Li, H., Bai, K., Wang, F.: Why attentions may not be interpretable? In: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pp. 25\u201334 (2021)","DOI":"10.1145\/3447548.3467307"},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Bastings, J., Filippova, K.: The elephant in the interpretability room: why use attention as explanation when we have saliency methods? arXiv preprint arXiv:2010.05607 (2020)","DOI":"10.18653\/v1\/2020.blackboxnlp-1.14"},{"key":"17_CR3","unstructured":"Bolya, D., Fu, C.Y., Dai, X., Zhang, P., Feichtenhofer, C., Hoffman, J.: Token merging: your VIT but faster. arXiv preprint arXiv:2210.09461 (2022)"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"Chefer, H., Gur, S., Wolf, L.: Transformer interpretability beyond attention visualization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 782\u2013791 (2021)","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Chen, X., He, K.: Exploring simple siamese representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15750\u201315758 (2021)","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Chen, X., Xie, S., He, K.: An empirical study of training self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9640\u20139649 (2021)","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"17_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":"17_CR9","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1038\/s42256-020-00257-z","volume":"2","author":"R Geirhos","year":"2020","unstructured":"Geirhos, R., et al.: Shortcut learning in deep neural networks. Nat. Mach. Intell. 2(11), 665\u2013673 (2020)","journal-title":"Nat. Mach. Intell."},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Haurum, J.B., Escalera, S., Taylor, G.W., Moeslund, T.B.: Which tokens to use? Investigating token reduction in vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 773\u2013783 (2023)","DOI":"10.1109\/ICCVW60793.2023.00085"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"17_CR13","unstructured":"Jain, S., et al.: Missingness bias in model debugging. arXiv preprint arXiv:2204.08945 (2022)"},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Long, S., Zhao, Z., Pi, J., Wang, S., Wang, J.: Beyond attentive tokens: incorporating token importance and diversity for efficient vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10334\u201310343 (2023)","DOI":"10.1109\/CVPR52729.2023.00996"},{"key":"17_CR15","unstructured":"Madsen, A., Reddy, S., Chandar, S.: Faithfulness measurable masked language models. arXiv preprint arXiv:2310.07819 (2023)"},{"key":"17_CR16","unstructured":"Matsoukas, C., Haslum, J.F., S\u00f6derberg, M., Smith, K.: Is it time to replace CNNs with transformers for medical images? arXiv preprint arXiv:2108.09038 (2021)"},{"key":"17_CR17","unstructured":"Ozbulak, U., et al.: Know your self-supervised learning: a survey on image-based generative and discriminative training. arXiv preprint arXiv:2305.13689 (2023)"},{"key":"17_CR18","unstructured":"Pan, B., Panda, R., Jiang, Y., Wang, Z., Feris, R., Oliva, A.: IA-RED$$^{2}$$: interpretability-aware redundancy reduction for vision transformers. In: Advances in Neural Information Processing Systems, vol. 34, pp. 24898\u201324911 (2021)"},{"key":"17_CR19","unstructured":"Renggli, C., Pinto, A.S., Houlsby, N., Mustafa, B., Puigcerver, J., Riquelme, C.: Learning to merge tokens in vision transformers. arXiv preprint arXiv:2202.12015 (2022)"},{"key":"17_CR20","unstructured":"Rigotti, M., Miksovic, C., Giurgiu, I., Gschwind, T., Scotton, P.: Attention-based interpretability with concept transformers. In: International Conference on Learning Representations (2021)"},{"issue":"3","key":"17_CR21","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"17_CR22","doi-asserted-by":"crossref","unstructured":"Serrano, S., Smith, N.A.: Is attention interpretable? arXiv preprint arXiv:1906.03731 (2019)","DOI":"10.18653\/v1\/P19-1282"},{"key":"17_CR23","doi-asserted-by":"crossref","unstructured":"Shamshad, F., et al.: Transformers in medical imaging: a survey. Med. Image Anal. 102802 (2023)","DOI":"10.1016\/j.media.2023.102802"},{"key":"17_CR24","doi-asserted-by":"crossref","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (2015)","DOI":"10.1109\/ICCV.2015.314"},{"key":"17_CR25","unstructured":"Singhal, K., et al.: Towards expert-level medical question answering with large language models. arXiv preprint arXiv:2305.09617 (2023)"},{"key":"17_CR26","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1007\/978-3-031-43895-0_40","volume-title":"MICCAI 2023","author":"S Sun","year":"2023","unstructured":"Sun, S., Koch, L.M., Baumgartner, C.F.: Right for the wrong reason: can interpretable ml techniques detect spurious correlations? In: Greenspan, H., et al. (eds.) MICCAI 2023. LNCS, vol. 14221, pp. 425\u2013434. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-43895-0_40"},{"key":"17_CR27","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"17_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12880-020-00482-3","volume":"20","author":"W Wang","year":"2020","unstructured":"Wang, W., Tian, J., Zhang, C., Luo, Y., Wang, X., Li, J.: An improved deep learning approach and its applications on colonic polyp images detection. BMC Med. Imaging 20, 1\u201314 (2020)","journal-title":"BMC Med. Imaging"},{"key":"17_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1007\/978-3-319-10590-1_53","volume-title":"Computer Vision \u2013 ECCV 2014","author":"MD Zeiler","year":"2014","unstructured":"Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818\u2013833. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10590-1_53"},{"key":"17_CR30","doi-asserted-by":"crossref","unstructured":"Zeng, W., et al.: Not all tokens are equal: human-centric visual analysis via token clustering transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11101\u201311111 (2022)","DOI":"10.1109\/CVPR52688.2022.01082"}],"container-title":["Lecture Notes in Computer Science","Machine Learning in Medical Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73290-4_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T00:36:01Z","timestamp":1732926961000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73290-4_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,23]]},"ISBN":["9783031732928","9783031732904"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73290-4_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,23]]},"assertion":[{"value":"23 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MLMI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Machine Learning in Medical Imaging","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Marrakesh","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Morocco","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mlmi-med2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/sites.google.com\/view\/mlmi2024","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}