{"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":1782394542116,"version":"3.54.5"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031439063","type":"print"},{"value":"9783031439070","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\/978-3-031-43907-0_61","type":"book-chapter","created":{"date-parts":[[2023,9,30]],"date-time":"2023-09-30T23:08:57Z","timestamp":1696115337000},"page":"637-647","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":34,"title":["M-FLAG: Medical Vision-Language Pre-training with Frozen Language Models and Latent Space Geometry Optimization"],"prefix":"10.1007","author":[{"given":"Che","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sibo","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengyun","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weitong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anand","family":"Shah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjia","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rossella","family":"Arcucci","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,10,1]]},"reference":[{"key":"61_CR1","doi-asserted-by":"publisher","unstructured":"Boecking, B., Usuyama, N., Bannur, S., Castro, D.C., Schwaighofer, A., et al.: Making the most of text semantics to improve biomedical vision-language processing. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, 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":"61_CR2","first-page":"100134","volume":"6","author":"J Chai","year":"2021","unstructured":"Chai, J., Zeng, H., Li, A., Ngai, E.W.: Deep learning in computer vision: a critical review of emerging techniques and application scenarios. Mach. Learn. Appl. 6, 100134 (2021)","journal-title":"Mach. Learn. Appl."},{"key":"61_CR3","unstructured":"Chen, M., et al.: Perfectly balanced: improving transfer and robustness of supervised contrastive learning. In: International Conference on Machine Learning (2022)"},{"key":"61_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 (2020)"},{"key":"61_CR5","unstructured":"Chen, Y., Liu, C., Huang, W., Cheng, S., Arcucci, R., Xiong, Z.: Generative text-guided 3D vision-language pretraining for unified medical image segmentation. arXiv preprint arXiv:2306.04811 (2023)"},{"key":"61_CR6","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT (2019)"},{"issue":"1","key":"61_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41746-020-00376-2","volume":"4","author":"A Esteva","year":"2021","unstructured":"Esteva, A., Chou, K., Yeung, S., Naik, N., Madani, A., et al.: Deep learning-enabled medical computer vision. NPJ Digital Med. 4(1), 1\u20139 (2021)","journal-title":"NPJ Digital Med."},{"key":"61_CR8","unstructured":"Fu, Y., Lapata, M.: Latent topology induction for understanding contextualized representations. arXiv preprint arXiv:2206.01512 (2022)"},{"key":"61_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"61_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"61_CR11","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: IEEE\/CVF International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00391"},{"key":"61_CR12","doi-asserted-by":"crossref","unstructured":"Irvin, J., Rajpurkar, P., Ko, M., Yu, Y., Ciurea-Ilcus, S., et al.: CheXpert: a large chest radiograph dataset with uncertainty labels and expert comparison. In: AAAI Conference on Artificial Intelligence (2019)","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"61_CR13","doi-asserted-by":"crossref","unstructured":"Izsak, P., Berchansky, M., Levy, O.: How to train BERT with an academic budget. arXiv preprint arXiv:2104.07705 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.831"},{"key":"61_CR14","unstructured":"Jing, L., Vincent, P., LeCun, Y., Tian, Y.: Understanding dimensional collapse in contrastive self-supervised learning. In: International Conference on Learning Representations (2021)"},{"key":"61_CR15","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, 317 (2019)","journal-title":"Sci. Data"},{"key":"61_CR16","unstructured":"Johnson, A.E., Pollard, T.J., Greenbaum, N.R., Lungren, M.P., Deng, C.Y., et al.: MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs. arXiv:1901.07042 (2019)"},{"key":"61_CR17","unstructured":"Langer, S.G., Shih, G.: SIIM-ACR Pneumothorax Segmentation (2019)"},{"key":"61_CR18","unstructured":"Li, J., Liu, C., Cheng, S., Arcucci, R., Hong, S.: Frozen language model helps ECG zero-shot learning. arXiv preprint arXiv:2303.12311 (2023)"},{"key":"61_CR19","doi-asserted-by":"crossref","unstructured":"Li, Y., Fan, H., Hu, R., Feichtenhofer, C., He, K.: Scaling language-image pre-training via masking. arXiv preprint arXiv:2212.00794 (2022)","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"61_CR20","first-page":"1","volume":"60","author":"D Quan","year":"2022","unstructured":"Quan, D., et al.: Deep feature correlation learning for multi-modal remote sensing image registration. IEEE Trans. Geosci. Remote Sens. 60, 1\u201316 (2022)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"61_CR21","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (2021)"},{"key":"61_CR22","unstructured":"Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"61_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"61_CR24","unstructured":"Seyyed-Kalantari, L., Liu, G., McDermott, M., Chen, I.Y., Ghassemi, M.: CheXclusion: fairness gaps in deep chest X-ray classifiers. In: Biocomputing (2021)"},{"issue":"1","key":"61_CR25","doi-asserted-by":"publisher","first-page":"e180041","DOI":"10.1148\/ryai.2019180041","volume":"1","author":"G Shih","year":"2019","unstructured":"Shih, G., Wu, C.C., Halabi, S.S., Kohli, M.D., Prevedello, L.M., 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":"61_CR26","unstructured":"Wan, Z., et al.: Med-UniC: unifying cross-lingual medical vision-language pre-training by diminishing bias. arXiv preprint arXiv:2305.19894 (2023)"},{"key":"61_CR27","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. Neural Inf. Process. Syst. 35, 33536\u201333549 (2022)","journal-title":"Neural Inf. Process. Syst."},{"key":"61_CR28","unstructured":"Wang, T., Isola, P.: Understanding contrastive representation learning through alignment and uniformity on the hypersphere. In: International Conference on Machine Learning (2020)"},{"key":"61_CR29","doi-asserted-by":"crossref","unstructured":"Wang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., Summers, R.M.: ChestX-ray8: hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In: IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.369"},{"issue":"1\u20133","key":"61_CR30","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/0169-7439(87)80084-9","volume":"2","author":"S Wold","year":"1987","unstructured":"Wold, S., Esbensen, K., Geladi, P.: Principal component analysis. Chemom. Intell. Lab. Syst. 2(1\u20133), 37\u201352 (1987)","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"61_CR31","unstructured":"You, Y., Li, J., Reddi, S., Hseu, J., Kumar, S., et al.: Large batch optimization for deep learning: training BERT in 76 minutes. In: International Conference on Learning Representations (2020)"},{"key":"61_CR32","unstructured":"Zhang, Y., Jiang, H., Miura, Y., Manning, C.D., Langlotz, C.P.: Contrastive learning of medical visual representations from paired images and text. arXiv preprint arXiv:2010.00747 (2020)"},{"key":"61_CR33","doi-asserted-by":"publisher","first-page":"100004","DOI":"10.1016\/j.array.2019.100004","volume":"3","author":"T Zhou","year":"2019","unstructured":"Zhou, T., Ruan, S., Canu, S.: A review: deep learning for medical image segmentation using multi-modality fusion. Array 3, 100004 (2019)","journal-title":"Array"},{"key":"61_CR34","unstructured":"Zhu, J.Y., et al.: Toward multimodal image-to-image translation. In: Advances in Neural Information Processing Systems (2017)"}],"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\/978-3-031-43907-0_61","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T18:30:13Z","timestamp":1709836213000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-43907-0_61"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031439063","9783031439070"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-43907-0_61","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)"}}]}}