{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T20:47:46Z","timestamp":1792270066630,"version":"4.4.0"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032049773","type":"print"},{"value":"9783032049780","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T00:00:00Z","timestamp":1758240000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T00:00:00Z","timestamp":1758240000000},"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\/978-3-032-04978-0_29","type":"book-chapter","created":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T16:16:11Z","timestamp":1758212171000},"page":"299-310","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Geometry-Guided Local Alignment for\u00a0Multi-view Visual Language Pre-training in\u00a0Mammography"],"prefix":"10.1007","author":[{"given":"Yuexi","family":"Du","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lihui","family":"Chen","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":[[2025,9,19]]},"reference":[{"issue":"2","key":"29_CR1","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1148\/radiol.2019182622","volume":"292","author":"A Akselrod-Ballin","year":"2019","unstructured":"Akselrod-Ballin, A., et al.: Predicting breast cancer by applying deep learning to linked health records and mammograms. Radiology 292(2), 331\u2013342 (2019)","journal-title":"Radiology"},{"key":"29_CR2","doi-asserted-by":"publisher","unstructured":"Alsentzer, E., McDermott, M., et\u00a0al.: Publicly available clinical BERT embeddings. In: Proceedings of the 2nd Clinical Natural Language Processing Workshop, pp. 72\u201378. Association for Computational Linguistics, Minneapolis (2019). https:\/\/doi.org\/10.18653\/v1\/W19-1909. https:\/\/www.aclweb.org\/anthology\/W19-1909","DOI":"10.18653\/v1\/W19-1909"},{"key":"29_CR3","unstructured":"Carr, C., et.al.: Rsna screening mammography breast cancer detection (2022). https:\/\/kaggle.com\/competitions\/rsna-breast-cancer-detection"},{"key":"29_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":"29_CR5","unstructured":"Chen, X., Yang, X., et\u00a0al.: 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":"29_CR6","doi-asserted-by":"publisher","unstructured":"Chen, Y., Carneiro, G., et\u00a0al.: Multi-view local co-occurrence and global consistency learning improve mammogram classification generalisation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 3\u201313. Springer, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-16437-8_1","DOI":"10.1007\/978-3-031-16437-8_1"},{"key":"29_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103192","volume":"96","author":"Y Chen","year":"2024","unstructured":"Chen, Y., et al.: Braixdet: learning to detect malignant breast lesion with incomplete annotations. Med. Image Anal. 96, 103192 (2024)","journal-title":"Med. Image Anal."},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Deng, J., Fei-Fei, L., et\u00a0al.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on CVPR, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"29_CR9","unstructured":"Dosovitskiy, A., Gelly, S., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Du, Y., Onofrey, J., Dvornek, N.C.: Multi-view and multi-scale alignment for contrastive language-image pre-training in mammography. arXiv preprint arXiv:2409.18119 (2024)","DOI":"10.1007\/978-3-031-96625-5_17"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Engeland, S.v., Timp, S., Karssemeijer, N.: Finding corresponding regions of interest in mediolateral oblique and craniocaudal mammographic views. Med. Phys. 33(9), 3203\u20133212 (2006)","DOI":"10.1118\/1.2230359"},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Ghosh, S., Batmanghelich, K., et\u00a0al.: 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":"29_CR13","doi-asserted-by":"publisher","unstructured":"Jain, K., Rangarajan, K., Arora, C.: Follow the radiologist: clinically relevant multi-view cues for breast cancer detection from mammograms. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 102\u2013112. Springer, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-3-031-72378-0_10","DOI":"10.1007\/978-3-031-72378-0_10"},{"key":"29_CR14","doi-asserted-by":"crossref","unstructured":"Jeong, J.J., Smith, G., 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":"29_CR15","doi-asserted-by":"publisher","unstructured":"Ji, C., Shen, D., et\u00a0al.: Mammo-net: integrating gaze supervision and interactive information in multi-view mammogram classification. In: MICCAI, pp. 68\u201378. Springer, Heidelberg (2023). https:\/\/doi.org\/10.1007\/978-3-031-43990-2_7","DOI":"10.1007\/978-3-031-43990-2_7"},{"key":"29_CR16","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1016\/j.inffus.2019.05.001","volume":"52","author":"A Jouirou","year":"2019","unstructured":"Jouirou, A., Ba\u00e2zaoui, A., Barhoumi, W.: Multi-view information fusion in mammograms: a comprehensive overview. Inf. Fusion 52, 308\u2013321 (2019)","journal-title":"Inf. Fusion"},{"key":"29_CR17","doi-asserted-by":"crossref","unstructured":"Liu, Y., Yu, Y., et\u00a0al.: Cross-view correspondence reasoning based on bipartite graph convolutional network for mammogram mass detection. In: Proceedings of the IEEE\/CVF Conference on CVPR, pp. 3812\u20133822 (2020)","DOI":"10.1109\/CVPR42600.2020.00387"},{"issue":"10","key":"29_CR18","doi-asserted-by":"publisher","first-page":"5947","DOI":"10.1109\/TPAMI.2021.3085783","volume":"44","author":"Y Liu","year":"2021","unstructured":"Liu, Y., Yu, Y., et al.: 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":"29_CR19","doi-asserted-by":"crossref","unstructured":"Ma, J., Li, X., Li, H., Wang, R., Menze, B., Zheng, W.S.: Cross-view relation networks for mammogram mass detection. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 8632\u20138638. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9413132"},{"key":"29_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103320","volume":"99","author":"F Manigrasso","year":"2025","unstructured":"Manigrasso, F., Morra, L., et al.: Mammography classification with multi-view deep learning techniques: investigating graph and transformer-based architectures. Med. Image Anal. 99, 103320 (2025)","journal-title":"Med. Image Anal."},{"key":"29_CR21","doi-asserted-by":"publisher","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, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-19809-0_30","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"29_CR22","unstructured":"Oquab, M., Bojanowski, P., et\u00a0al.: Dinov2: learning robust visual features without supervision (2023)"},{"key":"29_CR23","doi-asserted-by":"publisher","unstructured":"Pham, H.H., Trung, H.N., Nguyen, H.Q.: Vindr-mammo: a large-scale benchmark dataset for computer-aided detection and diagnosis in full-field digital mammography. Physionet (2022). https:\/\/doi.org\/10.13026\/br2v-7517","DOI":"10.13026\/br2v-7517"},{"key":"29_CR24","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":"29_CR25","doi-asserted-by":"crossref","unstructured":"Sahiner, B., Zhou, C., et\u00a0al.: Joint two-view information for computerized detection of microcalcifications on mammograms. Med. Phys. 33(7Part1), 2574\u20132585 (2006)","DOI":"10.1118\/1.2208919"},{"key":"29_CR26","doi-asserted-by":"crossref","unstructured":"Siegel, R., Ma, J., Zou, Z., Jemal, A.: Cancer statistics, 2014. CA Canc. J. Clin. 64(1) (2014)","DOI":"10.3322\/caac.21208"},{"key":"29_CR27","doi-asserted-by":"publisher","unstructured":"Sun, Z., Jiang, H., Ma, L., Yu, Z., Xu, H.: Transformer based multi-view network for mammographic image classification. In: MICCAI, pp. 46\u201354. Springer, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-16437-8_5","DOI":"10.1007\/978-3-031-16437-8_5"},{"key":"29_CR28","doi-asserted-by":"crossref","unstructured":"Sung, H., Bray, F., et\u00a0al.: Global cancer statistics 2020: globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Canc. J. Clin. 71(3), 209\u2013249 (2021)","DOI":"10.3322\/caac.21660"},{"key":"29_CR29","doi-asserted-by":"publisher","first-page":"33536","DOI":"10.52202\/068431-2430","volume":"35","author":"F Wang","year":"2022","unstructured":"Wang, F., Yu, L., et al.: 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":"29_CR30","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":"29_CR31","doi-asserted-by":"crossref","unstructured":"Wu, C., Zhang, X., Zhang, Y., Wang, Y., Xie, W.: Medklip: medical knowledge enhanced language-image pre-training. In: medRxiv, pp. 2023\u201301 (2023)","DOI":"10.1101\/2023.01.10.23284412"},{"key":"29_CR32","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1016\/j.neucom.2023.03.028","volume":"536","author":"L Xia","year":"2023","unstructured":"Xia, L., Gao, Z., et al.: Neural network model based on global and local features for multi-view mammogram classification. Neurocomputing 536, 21\u201329 (2023)","journal-title":"Neurocomputing"},{"key":"29_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102204","volume":"73","author":"Z Yang","year":"2021","unstructured":"Yang, Z., Huang, L., et al.: Momminet-v2: mammographic multi-view mass identification networks. Med. Image Anal. 73, 102204 (2021)","journal-title":"Med. Image Anal."},{"key":"29_CR34","doi-asserted-by":"publisher","unstructured":"You, K., Roh, B., et\u00a0al.: Cxr-clip: toward large scale chest x-ray language-image pre-training. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 101\u2013111. Springer, Heidelberg (2023). https:\/\/doi.org\/10.1007\/978-3-031-43895-0_10","DOI":"10.1007\/978-3-031-43895-0_10"},{"key":"29_CR35","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)"}],"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\/978-3-032-04978-0_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T18:41:09Z","timestamp":1787164869000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04978-0_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,19]]},"ISBN":["9783032049773","9783032049780"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04978-0_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,19]]},"assertion":[{"value":"19 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors\u00a0have no competing interests in this work and other related research.","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":"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"}}]}}