{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:57:28Z","timestamp":1783439848472,"version":"3.54.6"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030871956","type":"print"},{"value":"9783030871963","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-87196-3_26","type":"book-chapter","created":{"date-parts":[[2021,9,23]],"date-time":"2021-09-23T06:19:41Z","timestamp":1632377981000},"page":"273-283","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":30,"title":["Multimodal Representation Learning via Maximization of Local Mutual Information"],"prefix":"10.1007","author":[{"given":"Ruizhi","family":"Liao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Moyer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miriam","family":"Cha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keegan","family":"Quigley","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seth","family":"Berkowitz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Steven","family":"Horng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Polina","family":"Golland","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"William M.","family":"Wells","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,9,21]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Alsentzer, E., et al.: Publicly available clinical BERT embeddings. arXiv preprint arXiv:1904.03323 (2019)","DOI":"10.18653\/v1\/W19-1909"},{"key":"26_CR2","unstructured":"Belghazi, M.I., et al.: MINE: mutual information neural estimation. arXiv preprint arXiv:1801.04062 (2018)"},{"key":"26_CR3","unstructured":"Bojanowski, P., Joulin, A.: Unsupervised learning by predicting noise. In: International Conference on Machine Learning, pp. 517\u2013526. PMLR (2017)"},{"key":"26_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1007\/978-3-030-59713-9_51","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020","author":"G Chauhan","year":"2020","unstructured":"Chauhan, G., et al.: Joint Modeling of Chest Radiographs and Radiology Reports for Pulmonary Edema Assessment. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12262, pp. 529\u2013539. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59713-9_51"},{"key":"26_CR5","unstructured":"Chen, R.T., Li, X., Grosse, R., Duvenaud, D.: Isolating sources of disentanglement in variational autoencoders. arXiv preprint arXiv:1802.04942 (2018)"},{"key":"26_CR6","unstructured":"Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., Abbeel, P.: InfoGAN: interpretable representation learning by information maximizing generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2172\u20132180 (2016)"},{"issue":"2","key":"26_CR7","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1093\/jamia\/ocv080","volume":"23","author":"D Demner-Fushman","year":"2016","unstructured":"Demner-Fushman, D., et al.: Preparing a collection of radiology examinations for distribution and retrieval. J. Am. Med. Inform. Assoc. 23(2), 304\u2013310 (2016)","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"Harwath, D., Recasens, A., Sur\u00eds, D., Chuang, G., Torralba, A., Glass, J.: Jointly discovering visual objects and spoken words from raw sensory input. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 649\u2013665 (2018)","DOI":"10.1007\/978-3-030-01231-1_40"},{"key":"26_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"26_CR10","unstructured":"Hjelm, R.D., et al.: Learning deep representations by mutual information estimation and maximization. arXiv preprint arXiv:1808.06670 (2018)"},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"Horng, S., Liao, R., Wang, X., Dalal, S., Golland, P., Berkowitz, S.J.: Deep learning to quantify pulmonary edema in chest radiographs. Radiol. Artif. Intell. e190228 (2021)","DOI":"10.1148\/ryai.2021190228"},{"key":"26_CR12","doi-asserted-by":"crossref","unstructured":"Irvin, J., et al.: CheXpert: a large chest radiograph dataset with uncertainty labels and expert comparison. arXiv preprint arXiv:1901.07031 (2019)","DOI":"10.1609\/aaai.v33i01.3301590"},{"issue":"1","key":"26_CR13","doi-asserted-by":"publisher","first-page":"1","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), 1\u20138 (2019)","journal-title":"Sci. Data"},{"key":"26_CR14","unstructured":"Johnson, A.E., et al.: MIMIC-CXR-JPG - chest radiographs with structured labels (version 2.0.0). PhysioNet (2019). https:\/\/doi.org\/10.13026\/8360-t248"},{"key":"26_CR15","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":"26_CR16","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"26_CR17","unstructured":"Liao, R., Chauhan, G., Golland, P., Berkowitz, S.J., Horng, S.: Pulmonary edema severity grades based on MIMIC-CXR (version 1.0.1). PhysioNet (2021). https:\/\/doi.org\/10.13026\/rz5p-rc64"},{"key":"26_CR18","unstructured":"Liao, R., Moyer, D., Golland, P., Wells, W.M.: DEMI: discriminative estimator of mutual information. arXiv preprint arXiv:2010.01766 (2020)"},{"key":"26_CR19","unstructured":"Liao, R., et al.: Semi-supervised learning for quantification of pulmonary edema in chest x-ray images. arXiv preprint arXiv:1902.10785 (2019)"},{"issue":"2","key":"26_CR20","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1109\/42.563664","volume":"16","author":"F Maes","year":"1997","unstructured":"Maes, F., Collignon, A., Vandermeulen, D., Marchal, G., Suetens, P.: Multimodality image registration by maximization of mutual information. IEEE Trans. Med. Imaging 16(2), 187\u2013198 (1997)","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"4","key":"26_CR21","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1109\/TIT.1954.1057469","volume":"4","author":"W McGill","year":"1954","unstructured":"McGill, W.: Multivariate information transmission. Trans. IRE Prof. Group Inf. Theory 4(4), 93\u2013111 (1954)","journal-title":"Trans. IRE Prof. Group Inf. Theory"},{"key":"26_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1007\/978-3-319-46723-8_35","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2016","author":"M Moradi","year":"2016","unstructured":"Moradi, M., Guo, Y., Gur, Y., Negahdar, M., Syeda-Mahmood, T.: A cross-modality neural network transform for semi-automatic medical image annotation. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 300\u2013307. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46723-8_35"},{"key":"26_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1007\/978-3-030-00928-1_51","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2018","author":"M Moradi","year":"2018","unstructured":"Moradi, M., Madani, A., Gur, Y., Guo, Y., Syeda-Mahmood, T.: Bimodal network architectures for automatic generation of image annotation from text. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-L\u00f3pez, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11070, pp. 449\u2013456. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-00928-1_51"},{"key":"26_CR24","unstructured":"van den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"26_CR25","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using siamese BERT-networks. arXiv preprint arXiv:1908.10084 (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"26_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"808","DOI":"10.1007\/978-3-642-33783-3_58","volume-title":"Computer Vision \u2013 ECCV 2012","author":"S Rifai","year":"2012","unstructured":"Rifai, S., Bengio, Y., Courville, A., Vincent, P., Mirza, M.: Disentangling factors of variation for facial expression recognition. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7577, pp. 808\u2013822. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33783-3_58"},{"key":"26_CR27","unstructured":"Song, J., Ermon, S.: Understanding the limitations of variational mutual information estimators. In: International Conference on Learning Representations (2019)"},{"key":"26_CR28","doi-asserted-by":"crossref","unstructured":"Wang, X., Peng, Y., Lu, L., Lu, Z., Summers, R.M.: TienNet: text-image embedding network for common thorax disease classification and reporting in chest X-rays. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9049\u20139058 (2018)","DOI":"10.1109\/CVPR.2018.00943"},{"key":"26_CR29","unstructured":"Wang, X., et al.: Pulmonary edema severity estimation in chest radiographs using deep learning. In: International Conference on Medical Imaging with Deep Learning-Extended Abstract Track (2019)"},{"key":"26_CR30","doi-asserted-by":"crossref","unstructured":"Wells III, W.M., Viola, P., Atsumi, H., Nakajima, S., Kikinis, R.: Multi-modal volume registration by maximization of mutual information. Med. Image Anal. 1(1), 35\u201351 (1996)","DOI":"10.1016\/S1361-8415(01)80004-9"},{"key":"26_CR31","unstructured":"Wolf, T., et al.: Huggingface\u2019s transformers: state-of-the-art natural language processing. arXiv-1910 (2019)"},{"key":"26_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1007\/978-3-030-20351-1_10","volume-title":"Information Processing in Medical Imaging","author":"Y Xue","year":"2019","unstructured":"Xue, Y., Huang, X.: Improved disease classification in chest X-rays with transferred features from report generation. In: Chung, A.C.S., Gee, J.C., Yushkevich, P.A., Bao, S. (eds.) IPMI 2019. LNCS, vol. 11492, pp. 125\u2013138. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20351-1_10"},{"key":"26_CR33","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)"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-87196-3_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,23]],"date-time":"2021-09-23T06:47:34Z","timestamp":1632379654000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-87196-3_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030871956","9783030871963"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-87196-3_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"21 September 2021","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":"Strasbourg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 October 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/miccai2021.org\/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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1622","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":"531","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":"33% - 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":"4","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)"}},{"value":"The conference was held virtually.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}