{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:17:31Z","timestamp":1785543451808,"version":"3.56.0"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198083","type":"print"},{"value":"9783031198090","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-19809-0_39","type":"book-chapter","created":{"date-parts":[[2022,10,31]],"date-time":"2022-10-31T07:03:04Z","timestamp":1667199784000},"page":"685-701","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":69,"title":["Joint Learning of\u00a0Localized Representations from\u00a0Medical Images and\u00a0Reports"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8186-6479","authenticated-orcid":false,"given":"Philip","family":"M\u00fcller","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8382-8062","authenticated-orcid":false,"given":"Georgios","family":"Kaissis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Congyu","family":"Zou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5683-5889","authenticated-orcid":false,"given":"Daniel","family":"Rueckert","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,1]]},"reference":[{"key":"39_CR1","unstructured":"Bachman, P., Hjelm, R., Buchwalter, W.: Learning representations by maximizing mutual information across views. In: NeurIPS (2019)"},{"key":"39_CR2","unstructured":"Bardes, A., Ponce, J., LeCun, Y.: VICReg: variance-invariance-covariance regularization for self-supervised learning. In: ICLR (2022)"},{"key":"39_CR3","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. In: NeurIPS (2020)"},{"key":"39_CR4","doi-asserted-by":"publisher","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: ICCV, pp. 9630\u20139640 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00951","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"39_CR5","unstructured":"Chaitanya, K., Erdil, E., Karani, N., Konukoglu, E.: Contrastive learning of global and local features for medical image segmentation with limited annotations. In: NeurIPS (2020)"},{"key":"39_CR6","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: ICML (2020)"},{"key":"39_CR7","doi-asserted-by":"publisher","unstructured":"Chen, X., He, K.: Exploring simple Siamese representation learning. In: CVPR, pp. 15745\u201315753 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01549","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"39_CR8","doi-asserted-by":"publisher","unstructured":"Desai, K., Johnson, J.: VirTex: learning visual representations from textual annotations. In: CVPR, pp. 11157\u201311168 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01101","DOI":"10.1109\/CVPR46437.2021.01101"},{"key":"39_CR9","doi-asserted-by":"publisher","DOI":"10.7937\/tcia.2020.py71-5978","author":"S Desai","year":"2020","unstructured":"Desai, S., et al.: Data from chest imaging with clinical and genomic correlates representing a rural COVID-19 positive population [data set]. The Cancer Imaging Archive (2020). https:\/\/doi.org\/10.7937\/tcia.2020.py71-5978","journal-title":"The Cancer Imaging Archive"},{"key":"39_CR10","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL, pp. 4171\u20134186 (2019). https:\/\/doi.org\/10.18653\/v1\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"39_CR11","unstructured":"Ermolov, A., Siarohin, A., Sangineto, E., Sebe, N.: Whitening for self-supervised representation learning. In: ICML, pp. 3015\u20133024 (2021)"},{"key":"39_CR12","doi-asserted-by":"publisher","unstructured":"Gazda, M., Plavka, J., Gazda, J., Drot\u00e1r, P.: Self-supervised deep convolutional neural network for chest x-ray classification. IEEE Access, 151972\u2013151982 (2021). https:\/\/doi.org\/10.1109\/ACCESS.2021.3125324","DOI":"10.1109\/ACCESS.2021.3125324"},{"issue":"23","key":"39_CR13","first-page":"215","volume":"101","author":"A Goldberger","year":"2000","unstructured":"Goldberger, A., Amaral, L., Glass, L., Hausdorff, J., et al.: PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation [Online] 101(23), 215\u2013220 (2000)","journal-title":"Circulation [Online]"},{"key":"39_CR14","unstructured":"Grill, J.B., et al.: Bootstrap your own latent - a new approach to self-supervised learning. In: NeurIPS (2020)"},{"key":"39_CR15","doi-asserted-by":"publisher","unstructured":"He, K., Fan, H., Wu, Y., et al.: Momentum contrast for unsupervised visual representation learning. In: CVPR, pp. 9726\u20139735 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00975","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"39_CR16","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"39_CR17","unstructured":"Hjelm, R.D., et al.: Learning deep representations by mutual information estimation and maximization. In: ICLR (2019)"},{"key":"39_CR18","unstructured":"H\u00e9naff, O.J., Srinivas, A., et al.: Data-efficient image recognition with contrastive predictive coding. In: ICML, pp. 4182\u20134192 (2019)"},{"key":"39_CR19","doi-asserted-by":"crossref","unstructured":"Irvin, J., et al.: CheXpert: a large chest radiograph dataset with uncertainty labels and expert comparison. In: AAAI, pp. 590\u2013597 (2019)","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"39_CR20","unstructured":"JF-Healthcare: object-CXR - automatic detection of foreign objects on chest x-rays. MIDL (2020). https:\/\/jfhealthcare.github.io\/object-CXR\/"},{"key":"39_CR21","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: ICML (2021)"},{"key":"39_CR22","unstructured":"Johnson, A., Lungren, M., Peng, Y., et al.: MIMIC-CXR-JPG - chest radiographs with structured labels (version 2.0.0). PhysioNet (2019). https:\/\/doi.org\/10.13026\/8360-t248"},{"key":"39_CR23","doi-asserted-by":"publisher","unstructured":"Johnson, A., Pollard, T., Berkowitz, S., et al.: MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports. Sci. Data 6(317) (2019). https:\/\/doi.org\/10.1038\/s41597-019-0322-0","DOI":"10.1038\/s41597-019-0322-0"},{"key":"39_CR24","unstructured":"Johnson, A., Pollard, T., Mark, R., Berkowitz, S., Horng, S.: MIMIC-CXR database (version 2.0.0). PhysioNet (2019). https:\/\/doi.org\/10.13026\/C2JT1Q"},{"key":"39_CR25","unstructured":"Li, J., Zhou, P., Xiong, C., Hoi, S.C.H.: Prototypical contrastive learning of unsupervised representations. In: ICLR (2021)"},{"key":"39_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/978-3-030-87196-3_26","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"R Liao","year":"2021","unstructured":"Liao, R., et al.: Multimodal representation learning via maximization of local mutual information. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12902, pp. 273\u2013283. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87196-3_26"},{"key":"39_CR27","doi-asserted-by":"publisher","unstructured":"Liu, Z., Stent, S., Li, J., Gideon, J., Han, S.: LocTex: learning data-efficient visual representations from localized textual supervision. In: ICCV, pp. 2147\u20132156 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00217","DOI":"10.1109\/ICCV48922.2021.00217"},{"key":"39_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1007\/978-3-030-20873-8_7","volume-title":"Computer Vision \u2013 ACCV 2018","author":"A Mahendran","year":"2019","unstructured":"Mahendran, A., Thewlis, J., Vedaldi, A.: Cross pixel optical-flow similarity for self-supervised learning. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11365, pp. 99\u2013116. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20873-8_7"},{"key":"39_CR29","doi-asserted-by":"publisher","unstructured":"Misra, I., van der Maaten, L.: Self-supervised learning of pretext-invariant representations. In: CVPR, pp. 6706\u20136716 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00674","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"39_CR30","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1007\/978-3-031-16443-9_62","volume-title":"Medical Image Computing and Computer Assisted Intervention - MICCAI 2022","author":"P M\u00fcller","year":"2022","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.) MICCAI 2022. LNCS, vol. 13435, pp. 647\u2013657. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-16443-9_62"},{"key":"39_CR31","unstructured":"van den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv: 1807.03748 (2019)"},{"key":"39_CR32","unstructured":"Pinheiro, P.O., Almahairi, A., Benmalek, R.Y., Golemo, F., Courville, A.: Unsupervised learning of dense visual representations. In: NeurIPS (2020)"},{"key":"39_CR33","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763 (2021)"},{"key":"39_CR34","unstructured":"Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. arXiv preprint arXiv: 1804.02767 (2018)"},{"key":"39_CR35","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"},{"issue":"3","key":"39_CR36","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211\u2013252 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Int. J. Comput. Vision"},{"key":"39_CR37","series-title":"Algorithms for Intelligent Systems","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1007\/978-981-15-3242-9_28","volume-title":"Advanced Computing Technologies and Applications","author":"V Saraf","year":"2020","unstructured":"Saraf, V., Chavan, P., Jadhav, A.: Deep learning challenges in medical imaging. In: Vasudevan, H., Michalas, A., Shekokar, N., Narvekar, M. (eds.) Advanced Computing Technologies and Applications. AIS, pp. 293\u2013301. Springer, Singapore (2020). https:\/\/doi.org\/10.1007\/978-981-15-3242-9_28"},{"key":"39_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1007\/978-3-030-58598-3_10","volume-title":"Computer Vision \u2013 ECCV 2020","author":"MB Sariyildiz","year":"2020","unstructured":"Sariyildiz, M.B., Perez, J., Larlus, D.: Learning visual representations with\u00a0caption annotations. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12353, pp. 153\u2013170. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58598-3_10"},{"key":"39_CR39","doi-asserted-by":"publisher","unstructured":"Shih, G., et al.: Augmenting the national institutes of health chest radiograph dataset with expert annotations of possible pneumonia. Radiol. Artif. Intell. 1 (2019). https:\/\/doi.org\/10.1148\/ryai.2019180041","DOI":"10.1148\/ryai.2019180041"},{"key":"39_CR40","unstructured":"Society for Imaging Informatics in Medicine: SIIM-ACR pneumothorax segmentation (2019). https:\/\/www.kaggle.com\/c\/siim-acr-pneumothorax-segmentation"},{"key":"39_CR41","unstructured":"Sowrirajan, H., Yang, J., Ng, A.Y., Rajpurkar, P.: MoCo pretraining improves representation and transferability of chest x-ray models. In: MIDL (2021)"},{"key":"39_CR42","unstructured":"Sriram, A., et al.: COVID-19 prognosis via self-supervised representation learning and multi-image prediction. arXiv preprint arXiv: 2101.04909 (2021)"},{"key":"39_CR43","doi-asserted-by":"publisher","unstructured":"Tang, H., Sun, N., Li, Y.: Segmentation model of the opacity regions in the chest X-rays of the COVID-19 patients in the us rural areas and the application to the disease severity. medRxiv (2020). https:\/\/doi.org\/10.1101\/2020.10.19.20215483","DOI":"10.1101\/2020.10.19.20215483"},{"key":"39_CR44","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS (2017)"},{"key":"39_CR45","doi-asserted-by":"publisher","unstructured":"Wang, X., Peng, Y., Lu, L., et al.: ChestX-ray8: hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In: CVPR, pp. 3462\u20133471 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.369","DOI":"10.1109\/CVPR.2017.369"},{"key":"39_CR46","doi-asserted-by":"publisher","unstructured":"Wang, X., Zhang, R., Shen, C., Kong, T., Li, L.: Dense contrastive learning for self-supervised visual pre-training. In: CVPR, pp. 3023\u20133032 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00304","DOI":"10.1109\/CVPR46437.2021.00304"},{"key":"39_CR47","doi-asserted-by":"publisher","unstructured":"Wu, Z., Xiong, Y., Yu, S., Lin, D.: Unsupervised feature learning via non-parametric instance discrimination. In: CVPR, pp. 3733\u20133742 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00393","DOI":"10.1109\/CVPR.2018.00393"},{"key":"39_CR48","doi-asserted-by":"publisher","unstructured":"Xie, E., et al.: DetCo: unsupervised contrastive learning for object detection. In: ICCV, pp. 8372\u20138381 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00828","DOI":"10.1109\/ICCV48922.2021.00828"},{"key":"39_CR49","doi-asserted-by":"publisher","unstructured":"Xie, Z., Lin, Y., Zhang, Z., Cao, Y., Lin, S., Hu, H.: Propagate yourself: exploring pixel-level consistency for unsupervised visual representation learning. In: CVPR, pp. 16679\u201316688 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01641","DOI":"10.1109\/CVPR46437.2021.01641"},{"key":"39_CR50","unstructured":"Zbontar, J., Jing, L., Misra, I., LeCun, Y., Deny, S.: Barlow twins: self-supervised learning via redundancy reduction. In: ICML (2021)"},{"key":"39_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. arXiv preprint arXiv: 2010.00747 (2020)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19809-0_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T00:20:53Z","timestamp":1667434853000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19809-0_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198083","9783031198090"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19809-0_39","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"1 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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)"}}]}}