{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T13:35:42Z","timestamp":1782394542795,"version":"3.54.5"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031439032","type":"print"},{"value":"9783031439049","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-43904-9_48","type":"book-chapter","created":{"date-parts":[[2023,9,30]],"date-time":"2023-09-30T23:08:57Z","timestamp":1696115337000},"page":"493-503","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Contrastive Masked Image-Text Modeling for\u00a0Medical Visual Representation Learning"],"prefix":"10.1007","author":[{"given":"Cheng","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aoxiao","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dufan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quanzheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,10,1]]},"reference":[{"key":"48_CR1","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. Lecture Notes in Computer Science, vol. 13696, pp. 1\u201321. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20059-5_1","DOI":"10.1007\/978-3-031-20059-5_1"},{"key":"48_CR2","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":"48_CR3","doi-asserted-by":"publisher","unstructured":"Chen, Z., Du, Y., Hu, J., Liu, Y., Li, G., Wan, X., Chang, T.: Multi-modal masked autoencoders for medical vision-and-language pre-training. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds.) Medical Image Computing and Computer Assisted Intervention - MICCAI, Singapore, September 18\u201322, 2022, Proceedings, Part V, vol. 13435, pp. 679\u2013689. Springer (2022), https:\/\/doi.org\/10.1007\/978-3-031-16443-9_65","DOI":"10.1007\/978-3-031-16443-9_65"},{"issue":"9","key":"48_CR4","doi-asserted-by":"publisher","first-page":"1342","DOI":"10.1038\/s41591-018-0107-6","volume":"24","author":"J De Fauw","year":"2018","unstructured":"De Fauw, J., et al.: Clinically applicable deep learning for diagnosis and referral in retinal disease. Nat. Med. 24(9), 1342\u20131350 (2018)","journal-title":"Nat. Med."},{"key":"48_CR5","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Burstein, J., Doran, C., Solorio, T. (eds.) Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT, Minneapolis, MN, USA, June 2\u20137, 2019, vol. 1, pp. 4171\u20134186 (2019), https:\/\/doi.org\/10.18653\/v1\/n19-1423","DOI":"10.18653\/v1\/n19-1423"},{"key":"48_CR6","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: 9th International Conference on Learning Representations, ICLR (2021)"},{"issue":"7639","key":"48_CR7","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1038\/nature21056","volume":"542","author":"A Esteva","year":"2017","unstructured":"Esteva, A., et al.: Dermatologist-level classification of skin cancer with deep neural networks. Nature 542(7639), 115\u2013118 (2017)","journal-title":"Nature"},{"key":"48_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"48_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"48_CR10","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":"48_CR11","unstructured":"Huang, Z., et al.: Contrastive masked autoencoders are stronger vision learners. arXiv preprint arXiv:2207.13532 (2022)"},{"key":"48_CR12","doi-asserted-by":"crossref","unstructured":"Irvin, J., et al.: CheXpert: a large chest radiograph dataset with uncertainty labels and expert comparison. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 590\u2013597 (2019)","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"48_CR13","unstructured":"Jiang, Z., et al.: Layer grafted pre-training: bridging contrastive learning and masked image modeling for label-efficient representations. arXiv preprint arXiv:2302.14138 (2023)"},{"issue":"1","key":"48_CR14","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1038\/s41597-019-0322-0","volume":"6","author":"AE Johnson","year":"2019","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)","journal-title":"Sci. Data"},{"key":"48_CR15","doi-asserted-by":"publisher","unstructured":"Liao, R., et al.: Multimodal representation learning via maximization of local mutual information. In: de Bruijne, M., Cattin, P.C., Cotin, S., Padoy, N., Speidel, S., Zheng, Y., Essert, C. (eds.) Medical Image Computing and Computer Assisted Intervention - MICCAI, Strasbourg, France, September 27 - October 1, 2021, Proceedings, Part II, vol. 12902, pp. 273\u2013283. Springer (2021), https:\/\/doi.org\/10.1007\/978-3-030-87196-3_26","DOI":"10.1007\/978-3-030-87196-3_26"},{"key":"48_CR16","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"48_CR17","unstructured":"Mishra, S., et al.: A simple, efficient and scalable contrastive masked autoencoder for learning visual representations. arXiv preprint arXiv:2210.16870 (2022)"},{"key":"48_CR18","doi-asserted-by":"publisher","unstructured":"M\u00fcller, P., Kaissis, G., Zou, C., Rueckert, D.: Radiological reports improve pre-training for localized imaging tasks on chest X-rays. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds.) Medical Image Computing and Computer Assisted Intervention - MICCAI, Singapore, September 18\u201322, 2022, Proceedings, Part V, vol. 13435, pp. 647\u2013657. Springer (2022), https:\/\/doi.org\/10.1007\/978-3-031-16443-9_62","DOI":"10.1007\/978-3-031-16443-9_62"},{"key":"48_CR19","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"48_CR20","unstructured":"Rajpurkar, P., et al.: CheXNet: radiologist-level pneumonia detection on chest X-rays with deep learning. arXiv preprint arXiv:1711.05225 (2017)"},{"issue":"1","key":"48_CR21","doi-asserted-by":"publisher","first-page":"e180041","DOI":"10.1148\/ryai.2019180041","volume":"1","author":"G Shih","year":"2019","unstructured":"Shih, G., et al.: Augmenting the national institutes of health chest radiograph dataset with expert annotations of possible pneumonia. Radiol. Artif. Intell. 1(1), e180041 (2019)","journal-title":"Radiol. Artif. Intell."},{"key":"48_CR22","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."},{"issue":"1","key":"48_CR23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-019-56847-4","volume":"10","author":"L Wang","year":"2020","unstructured":"Wang, L., Lin, Z.Q., Wong, A.: Covid-Net: a tailored deep convolutional neural network design for detection of Covid-19 cases from chest X-ray images. Sci. Rep. 10(1), 1\u201312 (2020)","journal-title":"Sci. Rep."},{"key":"48_CR24","doi-asserted-by":"crossref","unstructured":"Wang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., Summers, R.: ChestX-ray8: hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3462\u20133471 (2017)","DOI":"10.1109\/CVPR.2017.369"},{"key":"48_CR25","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":"10.1109\/ICCV51070.2023.01954"},{"key":"48_CR26","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)"},{"issue":"1","key":"48_CR27","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1038\/s42256-021-00425-9","volume":"4","author":"HY Zhou","year":"2022","unstructured":"Zhou, H.Y., Chen, X., Zhang, Y., Luo, R., Wang, L., Yu, Y.: Generalized radiograph representation learning via cross-supervision between images and free-text radiology reports. Nature Mach. Intell. 4(1), 32\u201340 (2022)","journal-title":"Nature Mach. Intell."},{"key":"48_CR28","unstructured":"Zhou, H., Lian, C., Wang, L., Yu, Y.: Advancing radiograph representation learning with masked record modeling. In: The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1\u20135, 2023 (2023)"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-43904-9_48","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,11]],"date-time":"2024-03-11T14:40:41Z","timestamp":1710168041000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-43904-9_48"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031439032","9783031439049"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-43904-9_48","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"1 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"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":"Vancouver, BC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2023\/en\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2250","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"730","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"32% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}