{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T10:01:59Z","timestamp":1789984919272,"version":"4.0.1"},"publisher-location":"Cham","reference-count":21,"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_24","type":"book-chapter","created":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T09:11:06Z","timestamp":1789981866000},"page":"250-259","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning to\u00a0Read Where to\u00a0Look: Disease-Aware Vision\u2013Language Pretraining for\u00a03D CT"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5159-9792","authenticated-orcid":false,"given":"Simon","family":"Ging","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0686-7361","authenticated-orcid":false,"given":"Philipp","family":"Arnold","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2613-3209","authenticated-orcid":false,"given":"Sebastian","family":"Walter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hani","family":"Alnahas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1213-6776","authenticated-orcid":false,"given":"Hannah","family":"Bast","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9022-6000","authenticated-orcid":false,"given":"Elmar","family":"Kotter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4455-7145","authenticated-orcid":false,"given":"Jiancheng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5759-4896","authenticated-orcid":false,"given":"Behzad","family":"Bozorgtabar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6282-8861","authenticated-orcid":false,"given":"Thomas","family":"Brox","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,22]]},"reference":[{"key":"24_CR1","unstructured":"Agrawal, K.K., et al.: Pillar-0: a new frontier for radiology foundation models. arXiv preprint arXiv:2511.17803 (2025)"},{"issue":"8112","key":"24_CR2","doi-asserted-by":"publisher","first-page":"1318","DOI":"10.1038\/s41586-026-10181-8","volume":"652","author":"L Blankemeier","year":"2026","unstructured":"Blankemeier, L., Kumar, A., Cohen, J.P., Liu, J., Liu, L., et al.: Merlin: a computed tomography vision-language foundation model and dataset. Nature 652(8112), 1318\u20131328 (2026). https:\/\/doi.org\/10.1038\/s41586-026-10181-8","journal-title":"Nature"},{"key":"24_CR3","unstructured":"Claessens, C., Viviers, C., D\u2019Amicantonio, G., Bondarev, E., van\u00a0der Sommen, F.: Scaling self-supervised and cross-modal pretraining for volumetric CT transformers. arXiv preprint arXiv:2511.17209 (2025)"},{"key":"24_CR4","doi-asserted-by":"publisher","unstructured":"Draelos, R.L., Dov, D., Mazurowski, M.A., Lo, J.Y., Henao, R., et al.: Machine-learning-based multiple abnormality prediction with large-scale chest computed tomography volumes. Med. Image Anal. 67, 101857 (2021). https:\/\/doi.org\/10.1016\/j.media.2020.101857","DOI":"10.1016\/j.media.2020.101857"},{"key":"24_CR5","unstructured":"Gemma Team: Gemma 3 technical report. arXiv preprint arXiv:2503.19786 (2025)"},{"key":"24_CR6","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-025-01599-y","author":"IE Hamamci","year":"2026","unstructured":"Hamamci, I.E., Er, S., Wang, C., Almas, F., Simsek, A.G., et al.: Generalist foundation models from a multimodal dataset for 3D computed tomography. Nat. Biomed. Eng. (2026). https:\/\/doi.org\/10.1038\/s41551-025-01599-y","journal-title":"Nat. Biomed. Eng."},{"key":"24_CR7","doi-asserted-by":"crossref","unstructured":"Huang, S.C., Huo, Z., Steinberg, E., Chiang, C.C., Langlotz, C.: INSPECT: a multimodal dataset for patient outcome prediction of pulmonary embolisms. In: Advances in Neural Information Processing Systems, Datasets and Benchmarks Track, vol. 36 (2023)","DOI":"10.52202\/075280-0779"},{"key":"24_CR8","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-026-01879-2","author":"Z Huemann","year":"2026","unstructured":"Huemann, Z., Church, S., Warner, J.D., Tran, D., Tie, X., et al.: ConTEXTual Net 3D: vision-language modeling in PET\/CT for visual grounding of positive findings. J. Imaging Inform. Med. (2026). https:\/\/doi.org\/10.1007\/s10278-026-01879-2","journal-title":"J. Imaging Inform. Med."},{"key":"24_CR9","doi-asserted-by":"publisher","unstructured":"Lai, H., Jiang, Z., Yao, Q., Wang, R., He, Z., et\u00a0al.: Bridged semantic alignment for zero-shot 3D medical image diagnosis. IEEE J. Biomed. Health Inform. 1\u201314 (2025). https:\/\/doi.org\/10.1109\/JBHI.2025.3629096","DOI":"10.1109\/JBHI.2025.3629096"},{"key":"24_CR10","doi-asserted-by":"publisher","unstructured":"Li, Y., Lai, H., Zhou, X., Ming, S., Ma, W., et\u00a0al.: More performant and scalable: Rethinking contrastive vision-language pre-training of radiology in the LLM era. In: Gee, J.C., Alexander, D.C., Hong, J., Iglesias, J.E., Sudre, C.H., et\u00a0al. (eds.) Medical Image Computing and Computer Assisted Intervention - MICCAI 2025. LNCS, vol. 15966, pp. 348\u2013357. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-032-04981-0_33","DOI":"10.1007\/978-3-032-04981-0_33"},{"key":"24_CR11","unstructured":"Li, Y., Chen, Y., Lai, Y., Zhong, J., Wildman, V., Yang, X.: MedVista3D: vision-language modeling for reducing diagnostic errors in 3D CT disease detection, understanding and reporting. arXiv preprint arXiv:2509.03800 (2025)"},{"key":"24_CR12","unstructured":"Qwen Team: Qwen3 technical report. arXiv preprint arXiv:2505.09388 (2025)"},{"key":"24_CR13","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"24_CR14","doi-asserted-by":"publisher","first-page":"j4683","DOI":"10.1136\/bmj.j4683","volume":"359","author":"A Rimmer","year":"2017","unstructured":"Rimmer, A.: Radiologist shortage leaves patient care at risk, warns royal college. BMJ 359, j4683 (2017). https:\/\/doi.org\/10.1136\/bmj.j4683","journal-title":"BMJ"},{"key":"24_CR15","unstructured":"Sellergren, A., Kazemzadeh, S., Jaroensri, T., Kiraly, A., Traverse, M.: MedGemma technical report. arXiv preprint arXiv:2507.05201 (2025)"},{"key":"24_CR16","unstructured":"Shui, Z., Zhang, J., Cao, W., Wang, S., Guo, R.: Large-scale and fine-grained vision-language pre-training for enhanced CT image understanding. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"24_CR17","unstructured":"Tschannen, M., Gritsenko, A., Wang, X., Naeem, M.F., Alabdulmohsin, I.: SigLIP 2: multilingual vision-language encoders with improved semantic understanding, localization, and dense features. arXiv preprint arXiv:2502.14786 (2025)"},{"key":"24_CR18","doi-asserted-by":"publisher","unstructured":"Yang, J., Li, C., Zhang, P., Xiao, B., Liu, C., et\u00a0al.: Unified contrastive learning in image-text-label space. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19141\u201319151. IEEE (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01857","DOI":"10.1109\/CVPR52688.2022.01857"},{"key":"24_CR19","doi-asserted-by":"publisher","unstructured":"You, K., Gu, J., Ham, J., Park, B., Kim, J., et\u00a0al.: CXR-CLIP: toward large scale chest X-ray language-image pre-training. In: Greenspan, H., Madabhushi, A., Mousavi, P., Salcudean, S.E., Duncan, J., et\u00a0al. (eds.) Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2023. LNCS, vol. 14221, pp. 101\u2013111. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-43895-0_10","DOI":"10.1007\/978-3-031-43895-0_10"},{"key":"24_CR20","doi-asserted-by":"publisher","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11941\u201311952. IEEE (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.01100","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"24_CR21","doi-asserted-by":"publisher","unstructured":"Zhang, S., Xu, Y., Usuyama, N., Xu, H., Bagga, J., et\u00a0al.: A multimodal biomedical foundation model trained from fifteen million image\u2013text pairs. NEJM AI 2(1), AIoa2400640 (2025). https:\/\/doi.org\/10.1056\/AIoa2400640","DOI":"10.1056\/AIoa2400640"}],"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_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T09:11:15Z","timestamp":1789981875000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-38059-3_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,22]]},"ISBN":["9783032380586","9783032380593"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-38059-3_24","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"}}]}}