{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:59:56Z","timestamp":1775231996401,"version":"3.50.1"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032054784","type":"print"},{"value":"9783032054791","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,28]],"date-time":"2025-09-28T00:00:00Z","timestamp":1759017600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,28]],"date-time":"2025-09-28T00:00:00Z","timestamp":1759017600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-05479-1_10","type":"book-chapter","created":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T05:16:10Z","timestamp":1758950170000},"page":"87-96","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Interpreting CT-Scans with\u00a0CLIP: An Explorative Study of\u00a0Attribution Methods for\u00a03D Vision-Language Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6949-0223","authenticated-orcid":false,"given":"David Avedis","family":"Injarabian","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7171-7359","authenticated-orcid":false,"given":"Joonas","family":"Ariva","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9625-3552","authenticated-orcid":false,"given":"Hendrik","family":"\u0160uvalov","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4644-8893","authenticated-orcid":false,"given":"Dmytro","family":"Fishman","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,28]]},"reference":[{"key":"10_CR1","doi-asserted-by":"publisher","first-page":"7091301","DOI":"10.1155\/2023\/7091301","volume":"2023","author":"B Sistaninejhad","year":"2023","unstructured":"Sistaninejhad, B., Rasi, H., Nayeri, P.: A review paper about deep learning for medical image analysis. Comput. Math. Methods Med. 2023, 7091301 (2023)","journal-title":"Comput. Math. Methods Med."},{"key":"10_CR2","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","volume":"42","author":"G Litjens","year":"2017","unstructured":"Litjens, G., et al.: A survey on deep learning in medical image analysis. Med. Image Anal. 42, 60\u201388 (2017)","journal-title":"Med. Image Anal."},{"key":"10_CR3","unstructured":"Hamamci, I.E., et al.: Developing generalist foundation models from a multimodal dataset for 3d computed tomography. arXiv preprint arXiv:2403.17834 (2024)"},{"key":"10_CR4","doi-asserted-by":"publisher","unstructured":"Chen, Y., Liu, C., Liu, X., Arcucci, R., Xiong, Z.: BIMCV-R: a landmark dataset for 3D CT text-image retrieval. In: Linguraru, M.G., et al. (eds.) Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024. MICCAI 2024. LNCS, vol. 15011. Springer, Cham . (2024).https:\/\/doi.org\/10.1007\/978-3-031-72120-5_12","DOI":"10.1007\/978-3-031-72120-5_12"},{"key":"10_CR5","unstructured":"Radford, A., et\u00a0al. Learning transferable visual models from natural language supervision. arXiv preprint arXiv: 2103.00020 (2021)"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Zhao, Z., et al.: Clip in medical imaging: a survey. Med. Image Anal., 103551 (2025)","DOI":"10.1016\/j.media.2025.103551"},{"key":"10_CR7","doi-asserted-by":"publisher","unstructured":"Lei, Y., Li, Z., Shen, Y., Zhang, J., Shan, H.: Clip-lung: textual knowledge-guided lung nodule malignancy prediction. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 403\u2013412. Springer (2023). https:\/\/doi.org\/10.1007\/978-3-031-43990-2_38","DOI":"10.1007\/978-3-031-43990-2_38"},{"key":"10_CR8","unstructured":"Lin, J., et al.: Ct-glip: 3d grounded language-image pretraining with ct scans and radiology reports for full-body scenarios. arXiv preprint arXiv:2404.15272 (2024)"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Abnar, S., Zuidema, W.: Quantifying attention flow in transformers. arXiv preprint arXiv: 2005.00928 (2020)","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Lin, Y., et al.: Clip is also an efficient segmenter: a text-driven approach for weakly supervised semantic segmentation. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 15305\u201315314 (2023)","DOI":"10.1109\/CVPR52729.2023.01469"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: Score-cam: score-weighted visual explanations for convolutional neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pages 24\u201325 (2020)","DOI":"10.1109\/CVPRW50498.2020.00020"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Chen, P., Li, Q., Biaz, S., Bui, T., Nguyen, A.: gscorecam: what objects is clip looking at? In: Proceedings of the Asian Conference on Computer Vision, pp. 1959\u20131975 (2022)","DOI":"10.1007\/978-3-031-26316-3_35"},{"key":"10_CR13","doi-asserted-by":"publisher","unstructured":"Hamamci, I.E. et al.: GenerateCT: text-conditional generation of 3D chest CT volumes. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision \u2013 ECCV 2024. ECCV 2024. LNCS, vol. 15137. Springer, Cham (2025).https:\/\/doi.org\/10.1007\/978-3-031-72986-7_8","DOI":"10.1007\/978-3-031-72986-7_8"},{"key":"10_CR14","doi-asserted-by":"publisher","unstructured":"Boecking, B. et al.: Making the most of text semantics to improve biomedical vision\u2013language processing. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13696. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20059-5_1","DOI":"10.1007\/978-3-031-20059-5_1"},{"key":"10_CR15","unstructured":"Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. In: International Conference on Machine Learning, pp. 3319\u20133328. PMLR (2017)"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE international Conference on Computer Vision, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"10_CR17","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":"10_CR18","unstructured":"Zhao, C., Wang, K., Hsiao, J.H., Chan, A.B.: Grad-eclip: Gradient-based visual and textual explanations for clip. arXiv preprint arXiv:2502.18816, (2025)"},{"key":"10_CR19","doi-asserted-by":"publisher","unstructured":"atamizadeh, A., Nath, V., Tang, Y., Yang, D., Roth, H.R., Xu, D.: Swin UNETR: swin transformers for semantic segmentation of brain tumors in MRI images. In: Crimi, A., Bakas, S. (eds.) Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries. BrainLes 2021. LNCS, vol. 12962. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-08999-2_22","DOI":"10.1007\/978-3-031-08999-2_22"}],"updated-by":[{"DOI":"10.1007\/978-3-032-05479-1_12","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T00:00:00Z","timestamp":1775260800000}}],"container-title":["Lecture Notes in Computer Science","Clinical Image-Based Procedures"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-05479-1_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:09:09Z","timestamp":1775228949000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-05479-1_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,28]]},"ISBN":["9783032054784","9783032054791"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-05479-1_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,28]]},"assertion":[{"value":"28 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"4 April 2026","order":2,"name":"change_date","label":"Change Date","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Correction","order":3,"name":"change_type","label":"Change Type","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"A correction has been published.","order":4,"name":"change_details","label":"Change Details","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that\u00a0are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interest"}},{"value":"CLIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Workshop on Clinical Image-Based Procedures","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Democratic People's Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"clip2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/miccai-clip.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}