{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T20:30:54Z","timestamp":1774557054848,"version":"3.50.1"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032051684","type":"print"},{"value":"9783032051691","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T00:00:00Z","timestamp":1758326400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T00:00:00Z","timestamp":1758326400000},"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\/978-3-032-05169-1_3","type":"book-chapter","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T21:49:10Z","timestamp":1758318550000},"page":"24-33","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Advancing Medical Representation Learning Through High-Quality Data"],"prefix":"10.1007","author":[{"given":"Negin","family":"Baghbanzadeh","sequence":"first","affiliation":[]},{"given":"Adibvafa","family":"Fallahpour","sequence":"additional","affiliation":[]},{"given":"Yasaman","family":"Parhizkar","sequence":"additional","affiliation":[]},{"given":"Franklin","family":"Ogidi","sequence":"additional","affiliation":[]},{"given":"Shuvendu","family":"Roy","sequence":"additional","affiliation":[]},{"given":"Sajad","family":"Ashkezari","sequence":"additional","affiliation":[]},{"given":"Vahid Reza","family":"Khazaie","sequence":"additional","affiliation":[]},{"given":"Michael","family":"Colacci","sequence":"additional","affiliation":[]},{"given":"Ali","family":"Etemad","sequence":"additional","affiliation":[]},{"given":"Arash","family":"Afkanpour","sequence":"additional","affiliation":[]},{"given":"Elham","family":"Dolatabadi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,20]]},"reference":[{"key":"3_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-End object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"3_CR2","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2020)"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Girdhar, R., et al.: Imagebind: one embedding space to bind them all. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15180\u201315190 (2023)","DOI":"10.1109\/CVPR52729.2023.01457"},{"issue":"1","key":"3_CR4","first-page":"723","volume":"13","author":"A Gretton","year":"2012","unstructured":"Gretton, A., Borgwardt, K.M., Rasch, M.J., Sch\u00f6lkopf, B., Smola, A.: A kernel two-sample test. J. Mach. Learn. Res. 13(1), 723\u2013773 (2012)","journal-title":"J. Mach. Learn. Res."},{"key":"3_CR5","unstructured":"Gu, Y., et al.: Domain-specific language model pretraining for biomedical natural language processing (2020)"},{"key":"3_CR6","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition (2015). https:\/\/arxiv.org\/abs\/1512.03385"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Huang, J.H., et\u00a0al.: Deepopht: medical report generation for retinal images via deep models and visual explanation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2442\u20132452 (2021)","DOI":"10.1109\/WACV48630.2021.00249"},{"key":"3_CR8","unstructured":"Hurst, A., et\u00a0al.: Gpt-4o system card. arXiv preprint arXiv:2410.21276 (2024)"},{"key":"3_CR9","unstructured":"Ikezogwo, W., et al.: Quilt-1m: One million image-text pairs for histopathology. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"3_CR10","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Jobin, K., Mondal, A., Jawahar, C.: Docfigure: a dataset for scientific document figure classification. In: 2019 International Conference on Document Analysis and Recognition Workshops (ICDARW), vol.\u00a01, pp. 74\u201379. IEEE (2019)","DOI":"10.1109\/ICDARW.2019.00018"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Johnson, A.E., et al.: Mimic-cxr, a de-identified publicly available database of chest radiographs with free-text reports. Sci. Data 6(1), 317 (2019)","DOI":"10.1038\/s41597-019-0322-0"},{"key":"3_CR13","doi-asserted-by":"publisher","unstructured":"Lin, W., et al.: Pmc-clip: contrastive language-image pre-training using biomedical documents. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 525\u2013536. Springer, Heidelberg (2023). https:\/\/doi.org\/10.1007\/978-3-031-43993-3_51","DOI":"10.1007\/978-3-031-43993-3_51"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Lin, Z., et al.: Medical visual question answering: a survey. Artif. Intell. Med. 102611 (2023)","DOI":"10.1016\/j.artmed.2023.102611"},{"key":"3_CR15","unstructured":"Liu, A., et\u00a0al.: Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437 (2024)"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Lozano, A., et\u00a0al.: Biomedica: an open biomedical image-caption archive, dataset, and vision-language models derived from scientific literature. arXiv preprint arXiv:2501.07171 (2025)","DOI":"10.1109\/CVPR52734.2025.01837"},{"key":"3_CR17","first-page":"21455","volume":"35","author":"T Nguyen","year":"2022","unstructured":"Nguyen, T., Ilharco, G., Wortsman, M., Oh, S., Schmidt, L.: Quality not quantity: on the interaction between dataset design and robustness of clip. Adv. Neural. Inf. Process. Syst. 35, 21455\u201321469 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1007\/978-3-030-01364-6_20","volume-title":"Intravascular Imaging and Computer Assisted Stenting and Large-Scale Annotation of Biomedical Data and Expert Label Synthesis","author":"O Pelka","year":"2018","unstructured":"Pelka, O., Koitka, S., R\u00fcckert, J., Nensa, F., Friedrich, C.M.: Radiology Objects in COntext (ROCO): A Multimodal Image Dataset. In: Stoyanov, D., et al. (eds.) LABELS\/CVII\/STENT -2018. LNCS, vol. 11043, pp. 180\u2013189. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01364-6_20"},{"key":"3_CR19","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"3_CR20","unstructured":"Redmon, J., Farhadi, A.: Yolov3: an incremental improvement (2018). https:\/\/arxiv.org\/abs\/1804.02767"},{"key":"3_CR21","unstructured":"Roy, S., et al.: Benchmarking vision-language contrastive methods for medical representation learning. arXiv preprint arXiv:2406.07450 (2024)"},{"key":"3_CR22","unstructured":"Schwenker, E., Jiang, W., Spreadbury, T., Ferrier, N., Cossairt, O., Chan, M.K.: Exsclaim! - an automated pipeline for the construction of labeled materials imaging datasets from literature. arXiv e-prints pp. arXiv\u20132103 (2021)"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Subramanian, S., Wang, L.L., et al.: Medicat: a dataset of medical images, captions, and textual references. arXiv preprint arXiv:2010.06000 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.191"},{"key":"3_CR24","unstructured":"Zhang, S., et\u00a0al.: Biomedclip: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs. arXiv preprint arXiv:2303.00915 (2023)"},{"key":"3_CR25","unstructured":"Zhao, Z., et\u00a0al.: Clip in medical imaging: a comprehensive survey. arXiv preprint arXiv:2312.07353 (2023)"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-05169-1_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T21:49:18Z","timestamp":1758318558000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-05169-1_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,20]]},"ISBN":["9783032051684","9783032051691"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-05169-1_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,20]]},"assertion":[{"value":"20 September 2025","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","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"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":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (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":"27 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}