{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T16:13:50Z","timestamp":1771949630467,"version":"3.50.1"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031120527","type":"print"},{"value":"9783031120534","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\/978-3-031-12053-4_46","type":"book-chapter","created":{"date-parts":[[2022,7,25]],"date-time":"2022-07-25T09:15:50Z","timestamp":1658740550000},"page":"623-635","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Improving Image Representations via\u00a0MoCo Pre-training for\u00a0Multimodal CXR Classification"],"prefix":"10.1007","author":[{"given":"Francesco","family":"Dalla Serra","sequence":"first","affiliation":[]},{"given":"Grzegorz","family":"Jacenk\u00f3w","sequence":"additional","affiliation":[]},{"given":"Fani","family":"Deligianni","sequence":"additional","affiliation":[]},{"given":"Jeff","family":"Dalton","sequence":"additional","affiliation":[]},{"given":"Alison Q.","family":"O\u2019Neil","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,7,25]]},"reference":[{"key":"46_CR1","doi-asserted-by":"crossref","unstructured":"Huang, S.C., Pareek, A., Seyyedi, S., Banerjee, I., Lungren, M.P.: Fusion of medical imaging and electronic health records using deep learning: A systematic review and implementation guidelines. Digital Medicine, no. 1 (2020)","DOI":"10.1038\/s41746-020-00341-z"},{"key":"46_CR2","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017). https:\/\/proceedings.neurips.cc\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"46_CR3","doi-asserted-by":"crossref","unstructured":"Jacenk\u00f3w, G., O\u2019Neil, A.Q., Tsaftaris, S.A.: Indication as prior knowledge for multimodal disease classification in chest radiographs with transformers. In: 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI)","DOI":"10.1109\/ISBI52829.2022.9761567"},{"key":"46_CR4","doi-asserted-by":"publisher","unstructured":"Hendricks, L.A., Mellor, J., Schneider, R., Alayrac, J.-B., Nematzadeh, A.: Decoupling the role of data, attention, and losses in multimodal transformers. Trans. Assoc. Comput. Linguistics 9, 570\u2013585 (2021). https:\/\/doi.org\/10.1162\/tacl_a_00385. https:\/\/aclanthology.org\/2021.tacl-1.35","DOI":"10.1162\/tacl_a_00385"},{"key":"46_CR5","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"46_CR6","unstructured":"Li, L.H., Yatskar, M., Yin, D., Hsieh, C.-J., Chang, K.-W.: VisualBERT: a simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557, 2019"},{"key":"46_CR7","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: ViLBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: Advances in Neural Information Processing Systems, 32 (2019)"},{"key":"46_CR8","unstructured":"Ren, S., He, K., Girshick, R., Sun, F.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in neural information processing systems, 28 (2015)"},{"key":"46_CR9","doi-asserted-by":"crossref","unstructured":"Krishna, R., et al.: Visual genome: Connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vis. 123(1), 32\u201373 (2017)","DOI":"10.1007\/s11263-016-0981-7"},{"key":"46_CR10","unstructured":"Huang, Z., Zeng, Z., Liu, B., Fu, D., Fu, R.: Pixel-BERT: Aligning image pixels with text by deep multi-modal transformers. arXiv preprint arXiv:2004.008492(020)"},{"key":"46_CR11","unstructured":"Aditya Ramesh, A., et al.: Zero-shot text-to-image generation. In International Conference on Machine Learning, pp. 8821\u20138831. PMLR (2021)"},{"key":"46_CR12","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020"},{"key":"46_CR13","doi-asserted-by":"crossref","unstructured":"Johnson, A.E.W., 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":"46_CR14","doi-asserted-by":"publisher","unstructured":"Johnson, A.E.W., et al.: MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports. Sci. Data 6(1), December 2019. https:\/\/doi.org\/10.1038\/s41597-019-0322-0. https:\/\/doi.org\/10.1038\/s41597-019-0322-0","DOI":"10.1038\/s41597-019-0322-0"},{"key":"46_CR15","doi-asserted-by":"crossref","unstructured":"Goldberger, A.L., et al.: Physiobank, physiotoolkit, and physionet: components of a new research resource for complex physiologic signals. Circulation 101(23), e215\u2013e220 (2000)","DOI":"10.1161\/01.CIR.101.23.e215"},{"key":"46_CR16","doi-asserted-by":"crossref","unstructured":"Demner-Fushman, D., et al.: Preparing a collection of radiology examinations for distribution and retrieval. J. Am. Med. Inf. Assoc. 23(2), 304\u2013310 (2016)","DOI":"10.1093\/jamia\/ocv080"},{"key":"46_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1007\/978-3-030-60946-7_11","volume-title":"Multimodal Learning for Clinical Decision Support and Clinical Image-Based Procedures","author":"T van Sonsbeek","year":"2020","unstructured":"van Sonsbeek, T., Worring, M.: Towards Automated Diagnosis with Attentive Multi-modal Learning Using Electronic Health Records and Chest X-Rays. In: Syeda-Mahmood, T., Drechsler, K., Greenspan, H., Madabhushi, A., Karargyris, A., Linguraru, M.G., Oyarzun Laura, C., Shekhar, R., Wesarg, S., Gonz\u00e1lez Ballester, M.\u00c1., Erdt, M. (eds.) CLIP\/ML-CDS -2020. LNCS, vol. 12445, pp. 106\u2013114. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-60946-7_11"},{"key":"46_CR18","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., Moyer, D., Cha, M., Quigley, K., Berkowitz, S., Horng, S., Golland, P., Wells, W.M.: 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.) MICCAI 2021. LNCS, vol. 12902, pp. 273\u2013283. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87196-3_26"},{"key":"46_CR19","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":"46_CR20","unstructured":"Sowrirajan, J.Y., Ng, A.Y., Rajpurkar, P.: MoCo pretraining improves representation and transferability of chest X-ray models. In: Medical Imaging with Deep Learning, pp. 728\u2013744. PMLR (2021)"},{"key":"46_CR21","doi-asserted-by":"crossref","unstructured":"Azizi, S., et al.: Big self-supervised models advance medical image classification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3478\u20133488 (2021)","DOI":"10.1109\/ICCV48922.2021.00346"},{"key":"46_CR22","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":"46_CR23","unstructured":"Vu, Y.N.T.: Medaug: contrastive learning leveraging patient metadata improves representations for chest x-ray interpretation. In: Machine Learning for Healthcare Conference, pp. 755\u2013769. PMLR (2021)"},{"key":"46_CR24","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, B.: Grad-cam: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE international Conference on Computer Vision, pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"46_CR25","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: Proceedings of the IEEE Conference on Computer vision and pattern recognition, pp. 2097\u20132106 (2017)","DOI":"10.1109\/CVPR.2017.369"},{"key":"46_CR26","unstructured":"Kiela, D., Bhooshan, S., Firooz, H., Testuggine, D.: Supervised multimodal bitransformers for classifying images and text. arXiv preprint arXiv:1909.02950 (2019)"},{"key":"46_CR27","unstructured":"Devlin, J., Chang Kenton, M.-W., Toutanova, L.K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT, pp. 4171\u20134186 (2019)"},{"key":"46_CR28","unstructured":"van den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"46_CR29","doi-asserted-by":"crossref","unstructured":"Irvin, J., et al.: CheXpert: 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":"46_CR30","unstructured":"Singh, A., et al.: MMF: A multimodal framework for vision and language research (2020). https:\/\/github.com\/facebookresearch\/mmf"},{"key":"46_CR31","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":"46_CR32","doi-asserted-by":"publisher","unstructured":"Yijia, Z., Chen, Q., Yang, Z., Lin, H., lu, Z.: BioWordVec, improving biomedical word embeddings with subword information and MeSH. Sci. Data 6, 05 2019. https:\/\/doi.org\/10.1038\/s41597-019-0055-0","DOI":"10.1038\/s41597-019-0055-0"},{"key":"46_CR33","unstructured":"Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. In: NIPS 2014 Workshop on Deep Learning, December 2014"}],"container-title":["Lecture Notes in Computer Science","Medical Image Understanding and Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-12053-4_46","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,8]],"date-time":"2024-02-08T08:09:37Z","timestamp":1707379777000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-12053-4_46"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031120527","9783031120534"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-12053-4_46","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":"25 July 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MIUA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Annual Conference on Medical Image Understanding and Analysis","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cambridge","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","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":"27 July 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miua2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.miua2022.com\/home","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}