{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T18:04:44Z","timestamp":1791914684492,"version":"4.3.4"},"publisher-location":"Cham","reference-count":54,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031966248","type":"print"},{"value":"9783031966255","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T00:00:00Z","timestamp":1754524800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T00:00:00Z","timestamp":1754524800000},"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\/978-3-031-96625-5_17","type":"book-chapter","created":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T07:08:58Z","timestamp":1754464138000},"page":"247-262","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Multi-view and\u00a0Multi-scale Alignment for\u00a0Contrastive Language-Image Pre-training in\u00a0Mammography"],"prefix":"10.1007","author":[{"given":"Yuexi","family":"Du","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John A.","family":"Onofrey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicha C.","family":"Dvornek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,8,7]]},"reference":[{"key":"17_CR1","doi-asserted-by":"publisher","unstructured":"Alsentzer, E., et al.: Publicly available clinical BERT embeddings. In: Proceedings of the 2nd Clinical Natural Language Processing Workshop, Minneapolis, Minnesota, USA, pp. 72\u201378. Association for Computational Linguistics (2019). https:\/\/doi.org\/10.18653\/v1\/W19-1909, https:\/\/www.aclweb.org\/anthology\/W19-1909","DOI":"10.18653\/v1\/W19-1909"},{"key":"17_CR2","unstructured":"Bolton, E., et\u00a0al.: BiomedLM: a 2.7 b parameter language model trained on biomedical text. arXiv preprint arXiv:2403.18421 (2024)"},{"key":"17_CR3","unstructured":"Carr, C., et al.: RSNA screening mammography breast cancer detection (2022). https:\/\/kaggle.com\/competitions\/rsna-breast-cancer-detection"},{"key":"17_CR4","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"17_CR5","unstructured":"Chen, X., et al.: MAMMO-clip: leveraging contrastive language-image pre-training (clip) for enhanced breast cancer diagnosis with multi-view mammography. arXiv preprint arXiv:2404.15946 (2024)"},{"key":"17_CR6","unstructured":"Delitzas, A., et al.: Multi-clip: contrastive vision-language pre-training for question answering tasks in 3d scenes. arXiv preprint arXiv:2306.02329 (2023)"},{"issue":"3","key":"17_CR7","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.232780","volume":"310","author":"J Donnelly","year":"2024","unstructured":"Donnelly, J., et al.: Asymmirai: interpretable mammography-based deep learning model for 1-5-year breast cancer risk prediction. Radiology 310(3), e232780 (2024)","journal-title":"Radiology"},{"key":"17_CR8","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"Du, Y., Hooley, R.J., Lewin, J., Dvornek, N.C.: Sift-DBT: self-supervised initialization and fine-tuning for imbalanced digital breast tomosynthesis image classification. arXiv preprint arXiv:2403.13148 (2024)","DOI":"10.1109\/ISBI56570.2024.10635723"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Eslami, S., Meinel, C., De\u00a0Melo, G.: Pubmedclip: how much does clip benefit visual question answering in the medical domain? In: Findings of the Association for Computational Linguistics: EACL 2023, pp. 1181\u20131193 (2023)","DOI":"10.18653\/v1\/2023.findings-eacl.88"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Ghosh, S., Poynton, C.B., Visweswaran, S., Batmanghelich, K.: Mammo-clip: a vision language foundation model to enhance data efficiency and robustness in mammography. arXiv preprint arXiv:2405.12255 (2024)","DOI":"10.1007\/978-3-031-72390-2_59"},{"key":"17_CR12","first-page":"21271","volume":"33","author":"JB Grill","year":"2020","unstructured":"Grill, J.B., Strub, F., Altch\u00e9, F., Tallec, C., Richemond, P., Buchatskaya, E., Doersch, C., Avila Pires, B., Guo, Z., Gheshlaghi Azar, M., et al.: Bootstrap your own latent-a new approach to self-supervised learning. Adv. Neural. Inf. Process. Syst. 33, 21271\u201321284 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. arXiv preprint arXiv:1911.05722 (2019)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"17_CR14","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Huang, S.C., Shen, L., Lungren, M.P., Yeung, S.: Gloria: a multimodal global-local representation learning framework for label-efficient medical image recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3942\u20133951 (2021)","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Irvin, J., et\u00a0al.: Chexpert: a large chest radiograph dataset with uncertainty labels and expert comparison. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a033, pp. 590\u2013597 (2019)","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Jeong, J.J., et\u00a0al.: The emory breast imaging dataset (embed): a racially diverse, granular dataset of 3.4 million screening and diagnostic mammographic images. Radiol. Artif. Intell. 5(1), e220047 (2023)","DOI":"10.1148\/ryai.220047"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Ji, Z., Shaikh, M.A., Moukheiber, D., Srihari, S.N., Peng, Y., Gao, M.: Improving joint learning of chest x-ray and radiology report by word region alignment. In: Machine Learning in Medical Imaging: 12th International Workshop, MLMI 2021, Held in Conjunction with MICCAI 2021, Strasbourg, France, September 27, 2021, Proceedings 12. pp. 110\u2013119. Springer (2021)","DOI":"10.1007\/978-3-030-87589-3_12"},{"key":"17_CR19","doi-asserted-by":"crossref","unstructured":"Johnson, A.E., et al.: Mimic-cxr-jpg, a large publicly available database of labeled chest radiographs. arXiv preprint arXiv:1901.07042 (2019)","DOI":"10.1038\/s41597-019-0322-0"},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Lai, Z., Li, Z., Oliveira, L.C., Chauhan, J., Dugger, B.N., Chuah, C.N.: Clipath: fFine-tune clip with visual feature fusion for pathology image analysis towards minimizing data collection efforts. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2374\u20132380 (2023)","DOI":"10.1109\/ICCVW60793.2023.00251"},{"key":"17_CR21","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: International Conference on Machine Learning, pp. 19730\u201319742. PMLR (2023)"},{"key":"17_CR22","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"17_CR23","unstructured":"Li, Y., et al.: Supervision exists everywhere: a data efficient contrastive language-image pre-training paradigm. arXiv preprint arXiv:2110.05208 (2021)"},{"key":"17_CR24","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Domain generalization for mammography detection via multi-style and multi-view contrastive learning. In: Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2021: 24th International Conference, Strasbourg, France, September 27\u2013October 1, 2021, Proceedings, Part VII 24, pp. 98\u2013108. Springer (2021)","DOI":"10.1007\/978-3-030-87234-2_10"},{"key":"17_CR25","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"17_CR26","doi-asserted-by":"crossref","unstructured":"Liu, J., et al.: MLIP: medical language-image pre-training with masked local representation learning. arXiv preprint arXiv:2401.01591 (2024)","DOI":"10.1109\/ISBI56570.2024.10635357"},{"key":"17_CR27","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"issue":"10","key":"17_CR28","doi-asserted-by":"publisher","first-page":"5947","DOI":"10.1109\/TPAMI.2021.3085783","volume":"44","author":"Y Liu","year":"2021","unstructured":"Liu, Y., Zhang, F., Chen, C., Wang, S., Wang, Y., Yu, Y.: Act like a radiologist: towards reliable multi-view correspondence reasoning for mammogram mass detection. IEEE Trans. Pattern Anal. Mach. Intell. 44(10), 5947\u20135961 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"17_CR29","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"17_CR30","doi-asserted-by":"crossref","unstructured":"Mu, N., Kirillov, A., Wagner, D., Xie, S.: Slip: self-supervision meets language-image pre-training. In: European Conference on Computer Vision, pp. 529\u2013544. Springer (2022)","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"17_CR31","doi-asserted-by":"crossref","unstructured":"Nguyen, H., Pham, H., Le, L., Dao, M., Lam, K.V.C.: An open dataset of chest x-rays with radiologist annotations. PhysioNet https:\/\/doi.org\/10.13026\/3akn-b287 (2021)","DOI":"10.1038\/s41597-022-01498-w"},{"key":"17_CR32","doi-asserted-by":"crossref","unstructured":"Onken, M., Eichelberg, M., Riesmeier, J., Jensch, P.: Digital imaging and communications in medicine. In: Biomedical Image Processing, pp. 427\u2013454. Springer (2010)","DOI":"10.1007\/978-3-642-15816-2_17"},{"key":"17_CR33","unstructured":"Oquab, M., et al.: Dinov2: learning robust visual features without supervision (2023)"},{"key":"17_CR34","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"issue":"8","key":"17_CR35","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., et al.: Language models are unsupervised multitask learners. OpenAI blog 1(8), 9 (2019)","journal-title":"OpenAI blog"},{"key":"17_CR36","doi-asserted-by":"crossref","unstructured":"Shah, K., Shah, A., Lau, C.P., de\u00a0Melo, C.M., Chellappa, R.: Multi-view action recognition using contrastive learning. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3381\u20133391 (2023)","DOI":"10.1109\/WACV56688.2023.00338"},{"key":"17_CR37","unstructured":"Sickles, E.A., D\u2019Orsi, C.J., Bassett, L.W., et\u00a0al.: ACR BI-RADS mammography. In: ACR BI-RADS Atlas, Breast Imaging Reporting and Data System. American College of Radiology, Reston, VA, 5th edn. (2013)"},{"key":"17_CR38","unstructured":"Song, D., Fu, X., Nie, W., Li, W., Liu, A.: MV-clip: multi-view clip for zero-shot 3d shape recognition. arXiv preprint arXiv:2311.18402 (2023)"},{"issue":"6","key":"17_CR39","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1049\/bme2.12076","volume":"11","author":"L Sun","year":"2022","unstructured":"Sun, L., et al.: Breast mass classification based on supervised contrastive learning and multi-view consistency penalty on mammography. IET Biometrics 11(6), 588\u2013600 (2022)","journal-title":"IET Biometrics"},{"key":"17_CR40","unstructured":"Sun, Q., Fang, Y., Wu, L., Wang, X., Cao, Y.: Eva-clip: Improved training techniques for clip at scale. arXiv preprint arXiv:2303.15389 (2023)"},{"key":"17_CR41","unstructured":"Sun, Q., Wang, J., Yu, Q., Cui, Y., Zhang, F., Zhang, X., Wang, X.: Eva-clip-18b: scaling clip to 18 billion parameters. arXiv preprint arXiv:2402.04252 (2024)"},{"key":"17_CR42","doi-asserted-by":"crossref","unstructured":"Sung, H., et al.: Global cancer statistics 2020: globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: Can. J. Clin. 71(3), 209\u2013249 (2021)","DOI":"10.3322\/caac.21660"},{"key":"17_CR43","unstructured":"Tan, M., Le, Q.: Efficientnet: Rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114. PMLR (2019)"},{"key":"17_CR44","unstructured":"Wan, Z., et al.: Med-unic: unifying cross-lingual medical vision-language pre-training by diminishing bias. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"17_CR45","first-page":"33536","volume":"35","author":"F Wang","year":"2022","unstructured":"Wang, F., Zhou, Y., Wang, S., Vardhanabhuti, V., Yu, L.: Multi-granularity cross-modal alignment for generalized medical visual representation learning. Adv. Neural. Inf. Process. Syst. 35, 33536\u201333549 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"17_CR46","doi-asserted-by":"crossref","unstructured":"Wang, P., Wells, W.M., Berkowitz, S., Horng, S., Golland, P.: Using multiple instance learning to build multimodal representations. In: International Conference on Information Processing in Medical Imaging, pp. 457\u2013470. Springer (2023)","DOI":"10.1007\/978-3-031-34048-2_35"},{"key":"17_CR47","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wu, Z., Agarwal, D., Sun, J.: Medclip: contrastive learning from unpaired medical images and text. arXiv preprint arXiv:2210.10163 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"17_CR48","doi-asserted-by":"crossref","unstructured":"Wu, C., Zhang, X., Zhang, Y., Wang, Y., Xie, W.: Medklip: medical knowledge enhanced language-image pre-training. medRxiv, pp. 2023\u201301 (2023)","DOI":"10.1101\/2023.01.10.23284412"},{"key":"17_CR49","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":"17_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Ma, Z., Gao, X., Shakiah, S., Gao, Q., Chai, J.: Groundhog: grounding large language models to holistic segmentation. arXiv preprint arXiv:2402.16846 (2024)","DOI":"10.1109\/CVPR52733.2024.01349"},{"key":"17_CR51","unstructured":"Zhang, Y., Jiang, H., Miura, Y., Manning, C.D., Langlotz, C.P.: Contrastive learning of medical visual representations from paired images and text. In: Machine Learning for Healthcare Conference, pp. 2\u201325. PMLR (2022)"},{"key":"17_CR52","unstructured":"Zhao, Z., et\u00a0al.: Clip in medical imaging: a comprehensive survey. arXiv preprint arXiv:2312.07353 (2023)"},{"key":"17_CR53","doi-asserted-by":"crossref","unstructured":"Zheng, K., et al.: Dreamlip: language-image pre-training with long captions. arXiv preprint arXiv:2403.17007 (2024)","DOI":"10.1007\/978-3-031-72649-1_5"},{"key":"17_CR54","unstructured":"Zhou, H.Y., Lian, C., Wang, L., Yu, Y.: Advancing radiograph representation learning with masked record modeling. arXiv preprint arXiv:2301.13155 (2023)"}],"container-title":["Lecture Notes in Computer Science","Information Processing in Medical Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-96625-5_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T13:20:25Z","timestamp":1777468825000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-96625-5_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,7]]},"ISBN":["9783031966248","9783031966255"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-96625-5_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,7]]},"assertion":[{"value":"7 August 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IPMI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Information Processing in Medical Imaging","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kos","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","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":"25 May 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 May 2025","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":"ipmi2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ipmi2025.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}