{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T15:16:28Z","timestamp":1783696588275,"version":"3.55.0"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T00:00:00Z","timestamp":1777852800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T00:00:00Z","timestamp":1777852800000},"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":["Int J CARS"],"DOI":"10.1007\/s11548-026-03676-2","type":"journal-article","created":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T18:32:42Z","timestamp":1777919562000},"page":"1141-1149","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Token-based fidelity scoring for trustworthy vision transformer interpretations in medical imaging"],"prefix":"10.1007","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3084-6034","authenticated-orcid":false,"given":"Utku","family":"Ozbulak","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Solha","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wesley","family":"De Neve","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joris","family":"Vankerschaver","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,4]]},"reference":[{"key":"3676_CR1","unstructured":"Alvarez-Melis D, Jaakkola TS (2018) On the robustness of interpretability methods. In: 2018 ICML Workshop on Human Interpretability in Machine Learning"},{"key":"3676_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2023.110786","volume":"162","author":"K Borys","year":"2023","unstructured":"Borys K, Schmitt YA, Nauta M, Seifert C, Kr\u00e4mer N, Friedrich CM, Nensa F (2023) Explainable ai in medical imaging: an overview for clinical practitioners-beyond saliency-based xai approaches. Eur J Radiol 162:110786","journal-title":"Eur J Radiol"},{"key":"3676_CR3","unstructured":"Brocki L, Chung,NC (2023) Fidelity of interpretability methods and perturbation artifacts in neural networks. In: International Conference on Learning Representations (ICLR) Tiny Papers"},{"key":"3676_CR4","unstructured":"Bykov K, H\u00f6hne M.M.C, M\u00fcller K.R, Nakajima S, Kloft M (2020) How much can I trust you? \u2013 Quantifying uncertainties in explaining neural networks. arXiv preprint arXiv:2006.09000"},{"key":"3676_CR5","doi-asserted-by":"crossref","unstructured":"Caron M, Touvron H, Misra I, J\u00e9gou H, Mairal J, Bojanowski P, Joulin A (2021) Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 9650\u20139660","DOI":"10.1109\/ICCV48922.2021.00951"},{"issue":"1","key":"3676_CR6","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1038\/s41746-022-00699-2","volume":"5","author":"H Chen","year":"2022","unstructured":"Chen H, Gomez C, Huang CM, Unberath M (2022) Explainable medical imaging ai needs human-centered design: guidelines and evidence from a systematic review. NPJ digital medicine 5(1):156","journal-title":"NPJ digital medicine"},{"key":"3676_CR7","doi-asserted-by":"crossref","unstructured":"Chen X, He K (2021) Exploring simple siamese representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 15750\u201315758","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"3676_CR8","doi-asserted-by":"crossref","unstructured":"Chung M, Won J.B, Kim G, Kim Y, Ozbulak U (2024) Evaluating visual explanations of attention maps for transformer-based medical imaging. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. pp. 110\u2013120. Springer","DOI":"10.1007\/978-3-031-77610-6_11"},{"key":"3676_CR9","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, Uszkoreit J, Houlsby N (2021) An image is worth 16x16 words: Transformers for image recognition at scale. In: International Conference on Learning Representations (ICLR)"},{"key":"3676_CR10","doi-asserted-by":"crossref","unstructured":"Fayyaz M, Koohpayegani S.A, Jafari F.R, Sengupta S, Joze H.R.V, Sommerlade E, Pirsiavash H, Gall J (2022) Adaptive token sampling for efficient vision transformers. In: European Conference on Computer Vision. pp. 396\u2013414. Springer","DOI":"10.1007\/978-3-031-20083-0_24"},{"key":"3676_CR11","doi-asserted-by":"crossref","unstructured":"Haurum JB, Escalera S, Taylor GW, Moeslund TB (2023) Which tokens to use? investigating token reduction in vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 773\u2013783","DOI":"10.1109\/ICCVW60793.2023.00085"},{"key":"3676_CR12","doi-asserted-by":"crossref","unstructured":"He J, Chen JN, Liu S, Kortylewski A, Yang C, Bai Y, Wang C (2022) Transfg: A transformer architecture for fine-grained recognition. In: Proceedings of the AAAI conference on artificial intelligence. vol.\u00a036, pp. 852\u2013860","DOI":"10.1609\/aaai.v36i1.19967"},{"key":"3676_CR13","doi-asserted-by":"crossref","unstructured":"He K, Chen X, Xie S, Li Y, Doll\u00e1r P, Girshick R (2022) Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 16000\u201316009","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"3676_CR14","doi-asserted-by":"crossref","unstructured":"Heo B, Yun S, Han D, Chun S, Choe J, Oh S.J (2021) Rethinking spatial dimensions of vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 11936\u201311945","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"3676_CR15","doi-asserted-by":"crossref","unstructured":"Hu Y, Jin X, Zhang Y, Hong H, Zhang J, He Y, Xue H (2021) Rams-trans: Recurrent attention multi-scale transformer for fine-grained image recognition. In: Proceedings of the 29th ACM International Conference on Multimedia. pp. 4239\u20134248","DOI":"10.1145\/3474085.3475561"},{"key":"3676_CR16","unstructured":"Jain S, Salman H, Wong E, Zhang P, Vineet V, Vemprala S, Madry A (2022) Missingness bias in model debugging. In: International Conference on Learning Representations"},{"key":"3676_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102684","volume":"84","author":"W Jin","year":"2023","unstructured":"Jin W, Li X, Fatehi M, Hamarneh G (2023) Guidelines and evaluation of clinical explainable ai in medical image analysis. Med Image Anal 84:102684","journal-title":"Med Image Anal"},{"key":"3676_CR18","doi-asserted-by":"crossref","unstructured":"Kang S, Vankerschaver J, Ozbulak U (2024) Identifying critical tokens for accurate predictions in transformer-based medical imaging models. In: International Workshop on Machine Learning in Medical Imaging. pp. 169\u2013179. Springer","DOI":"10.1007\/978-3-031-73290-4_17"},{"key":"3676_CR19","unstructured":"Li Z, Yang T, Wang P, Cheng J (2022) Q-vit: Fully differentiable quantization for vision transformer. arXiv preprint arXiv:2201.07703"},{"key":"3676_CR20","doi-asserted-by":"crossref","unstructured":"Lin Y, Zhang T, Sun P, Li Z, Zhou S (2022) Fq-vit: Post-training quantization for fully quantized vision transformer. In: Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI)","DOI":"10.24963\/ijcai.2022\/164"},{"key":"3676_CR21","doi-asserted-by":"crossref","unstructured":"Long S, Zhao Z, Pi J, Wang S, Wang J (2023) 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","DOI":"10.1109\/CVPR52729.2023.00996"},{"key":"3676_CR22","unstructured":"Madsen A, Reddy S, Chandar S (2024) Faithfulness measurable masked language models. In: Proceedings of the 41st International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0235, pp. 34161\u201334202"},{"issue":"1","key":"3676_CR23","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1038\/s41597-023-02100-7","volume":"10","author":"HT Nguyen","year":"2023","unstructured":"Nguyen HT, Nguyen HQ, Pham HH, Lam K, Le LT, Dao M, Vu V (2023) Vindr-mammo: a large-scale benchmark dataset for computer-aided diagnosis in full-field digital mammography. Scientific Data 10(1):277","journal-title":"Scientific Data"},{"key":"3676_CR24","first-page":"24898","volume":"34","author":"B Pan","year":"2021","unstructured":"Pan B, Panda R, Jiang Y, Wang Z, Feris R, Oliva A (2021) $$ia-red^{2}$$: interpretability-aware redundancy reduction for vision transformers. Adv Neural Inf Process Syst 34:24898\u201324911","journal-title":"Adv Neural Inf Process Syst"},{"key":"3676_CR25","unstructured":"Petsiuk V, Das A, Saenko K (2018) Rise: Randomized input sampling for explanation of black-box models. In: Proceedings of the British Machine Vision Conference (BMVC)"},{"key":"3676_CR26","unstructured":"Rajpurkar P, Irvin J, Bagul A, Ding D, Duan T, Mehta H, Yang B, Zhu K, Laird D, Ball R.L, et\u00a0al (2018) Mura: Large dataset for abnormality detection in musculoskeletal radiographs. In: Proceedings of the Conference on Medical Imaging with Deep Learning (MIDL)"},{"key":"3676_CR27","doi-asserted-by":"crossref","unstructured":"Ribeiro M.T, Singh S, Guestrin C (2016) \u201cWhy should I trust you?\u201d Explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. pp. 1135\u20131144","DOI":"10.1145\/2939672.2939778"},{"key":"3676_CR28","doi-asserted-by":"crossref","unstructured":"Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M, Berg AC, Fei-Fei L (2015) ImageNet large scale visual recognition challenge. Int J Comput Vision 115(3):211\u2013252","DOI":"10.1007\/s11263-015-0816-y"},{"key":"3676_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.105111","volume":"140","author":"Z Salahuddin","year":"2022","unstructured":"Salahuddin Z, Woodruff HC, Chatterjee A, Lambin P (2022) Transparency of deep neural networks for medical image analysis: a review of interpretability methods. Comput Biol Med 140:105111","journal-title":"Comput Biol Med"},{"key":"3676_CR30","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 (2020) An improved deep learning approach and its applications on colonic polyp images detection. BMC Med Imaging 20:1\u201314","journal-title":"BMC Med Imaging"},{"key":"3676_CR31","unstructured":"Yeh C.K, Hsieh C.Y, Suggala A, Inouye D.I, Ravikumar P.K (2019) On the (in) fidelity and sensitivity of explanations. Adv Neural Inf Process Syst 32"},{"key":"3676_CR32","doi-asserted-by":"crossref","unstructured":"Zeiler M.D, Fergus R (2014) Visualizing and understanding convolutional networks. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part I 13. pp. 818\u2013833. Springer","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"3676_CR33","doi-asserted-by":"crossref","unstructured":"Zeng W, Jin S, Liu W, Qian C, Luo P, Ouyang W, Wang X (2022) 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","DOI":"10.1109\/CVPR52688.2022.01082"},{"issue":"10","key":"3676_CR34","doi-asserted-by":"publisher","first-page":"1084","DOI":"10.1007\/s11263-017-1059-x","volume":"126","author":"J Zhang","year":"2018","unstructured":"Zhang J, Bargal SA, Lin Z, Brandt J, Shen X, Sclaroff S (2018) Top-down neural attention by excitation backprop. Int J Comput Vision 126(10):1084\u20131102","journal-title":"Int J Comput Vision"},{"key":"3676_CR35","unstructured":"Zheng X, Shirani F, Wang T, Cheng W, Chen Z, Chen H, Wei H, Luo D (2024) Towards robust fidelity for evaluating explainability of graph neural networks. In: The Twelfth International Conference on Learning Representations"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-026-03676-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-026-03676-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-026-03676-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:55:17Z","timestamp":1783695317000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-026-03676-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,4]]},"references-count":35,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["3676"],"URL":"https:\/\/doi.org\/10.1007\/s11548-026-03676-2","relation":{},"ISSN":["1861-6429"],"issn-type":[{"value":"1861-6429","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,4]]},"assertion":[{"value":"26 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"No new human or animal studies were performed. This work used publicly available, de-identified medical imaging datasets that were originally collected with appropriate ethical approval by the respective data providers.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Human and Animal Rights"}}]}}