{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T06:44:40Z","timestamp":1775198680063,"version":"3.50.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,1,20]],"date-time":"2022-01-20T00:00:00Z","timestamp":1642636800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,1,20]],"date-time":"2022-01-20T00:00:00Z","timestamp":1642636800000},"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":["Nat Mach Intell"],"DOI":"10.1038\/s42256-021-00425-9","type":"journal-article","created":{"date-parts":[[2022,1,20]],"date-time":"2022-01-20T12:02:36Z","timestamp":1642680156000},"page":"32-40","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":110,"title":["Generalized radiograph representation learning via cross-supervision between images and free-text radiology reports"],"prefix":"10.1038","volume":"4","author":[{"given":"Hong-Yu","family":"Zhou","sequence":"first","affiliation":[]},{"given":"Xiaoyu","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Yinghao","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Ruibang","family":"Luo","sequence":"additional","affiliation":[]},{"given":"Liansheng","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0470-5548","authenticated-orcid":false,"given":"Yizhou","family":"Yu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,1,20]]},"reference":[{"key":"425_CR1","unstructured":"Krizhevsky, A., Sutskever, I. & Hinton, G. E. ImageNet classification with deep convolutional neural networks. In Proc. 26th Advances in Neural Information Processing Systems 1097\u20131105 (NeurIPS, 2012)."},{"key":"425_CR2","unstructured":"Simonyan, K. & Zisserman, A. Very deep convolutional networks for large-scale image recognition. In 2nd International Conference on Learning Representations (ICLR, 2014)."},{"key":"425_CR3","doi-asserted-by":"crossref","unstructured":"Szegedy, C. et al. Going deeper with convolutions. In Proc. 28th IEEE Conference on Computer Vision and Pattern Recognition 1\u20139 (IEEE, 2015).","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"425_CR4","doi-asserted-by":"crossref","unstructured":"He, K. M., Zhang, X. Y., Ren, S. Q. & Sun, J. Deep residual learning for image recognition. In Proc. 29th IEEE Conference on Computer Vision and Pattern Recognition 770\u2013778 (IEEE, 2016).","DOI":"10.1109\/CVPR.2016.90"},{"key":"425_CR5","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., van der Maaten, L. & Weinberger, K. Q. Densely connected convolutional networks. In Proc. 30th IEEE Conference on Computer Vision and Pattern Recognition 4700\u20134708 (IEEE, 2017).","DOI":"10.1109\/CVPR.2017.243"},{"key":"425_CR6","doi-asserted-by":"crossref","unstructured":"Bengio, Y., Courville, A. & Vincent, P. Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35, 1798\u20131828 (IEEE, 2013).","DOI":"10.1109\/TPAMI.2013.50"},{"key":"425_CR7","unstructured":"Phillips, N.A. et al. CheXphoto: 10,000+ photos and transformations of chest X-rays for benchmarking deep learning robustness. In Proc. 5th Machine Learning for Health 318\u2013327 (PMLR, 2020)."},{"key":"425_CR8","doi-asserted-by":"crossref","unstructured":"Taylor, A. G., Mielke, C. & Mongan, J. Automated detection of moderate and large pneumothorax on frontal chest X-rays using deep convolutional neural networks: a retrospective study. PLoS Med. 15, e1002697 (2018).","DOI":"10.1371\/journal.pmed.1002697"},{"key":"425_CR9","doi-asserted-by":"crossref","unstructured":"Carlile, M. et al. Deployment of artificial intelligence for radiographic diagnosis of COVID-19 pneumonia in the emergency department. JACEP Open 1, 1459\u20131464 (2018).","DOI":"10.1002\/emp2.12297"},{"key":"425_CR10","unstructured":"Yosinski, J., Clune, J., Bengio, Y. & Lipson, H. How transferable are features in deep neural networks? In Proc. 28th Advances in Neural Information Processing Systems 3320\u20133328 (NeurIPS, 2014)."},{"key":"425_CR11","doi-asserted-by":"crossref","unstructured":"Wang, X.S. et al. ChestX-ray8: hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In Proc. 30th IEEE Conference on Computer Vision and Pattern Recognition 2097\u20132106 (IEEE, 2017).","DOI":"10.1109\/CVPR.2017.369"},{"key":"425_CR12","doi-asserted-by":"crossref","unstructured":"Deng, J. et al. ImageNet: a large-scale hierarchical image database. In Proc. 22nd IEEE Conference on Computer Vision and Pattern Recognition 248\u2013255 (IEEE, 2009).","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"425_CR13","doi-asserted-by":"crossref","unstructured":"Chen, L. et al. Self-supervised learning for medical image analysis using image context restoration. Med. Image Anal. 58, 101539 (2019).","DOI":"10.1016\/j.media.2019.101539"},{"key":"425_CR14","doi-asserted-by":"crossref","unstructured":"Zhou, Z. W., Sodha, V., Pang, J. X., Gotway, M. B. & Liang, J. M. Model genesis. Med. Image Anal. 67, 101840 (2021).","DOI":"10.1016\/j.media.2020.101840"},{"key":"425_CR15","doi-asserted-by":"crossref","unstructured":"Haghighi, F., Taher, M. R. H., Zhou, Z. W., Gotway, M. B. & Liang, J. M. Transferable visual words: exploiting the semantics of anatomical patterns for self-supervised learning. IEEE Trans. Med. Imag. 40, 2857-2868 (IEEE, 2021).","DOI":"10.1109\/TMI.2021.3060634"},{"key":"425_CR16","doi-asserted-by":"crossref","unstructured":"Zhou, H.-Y. et al. Comparing to learn: surpassing ImageNet pretraining on radiographs by comparing image representations. In Proc. 23rd International Conference on Medical Image Computing and Computer-Assisted Intervention 398\u2013407 (Springer, 2020).","DOI":"10.1007\/978-3-030-59710-8_39"},{"key":"425_CR17","doi-asserted-by":"crossref","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\u20138 (2019).","DOI":"10.1038\/s41597-019-0322-0"},{"key":"425_CR18","doi-asserted-by":"crossref","unstructured":"Irvin, J. et al. CheXpert: a large chest radiograph dataset with uncertainty labels and expert comparison. In Proc. 33rd AAAI Conference on Artificial Intelligence 590\u2013597 (AAAI, 2019).","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"425_CR19","unstructured":"Dosovitskiy, A. et al. An image is worth 16\u2009\u00d7\u200916 words: transformers for image recognition at scale. In 9th International Conference on Learning Representations (ICLR, 2021)."},{"key":"425_CR20","unstructured":"Vaswani, A. et al. Attention is all you need. In Proc. 31st Advances in Neural Information Processing Systems 5998\u20136008 (NeurIPS, 2017)."},{"key":"425_CR21","doi-asserted-by":"crossref","unstructured":"Shin, H.-C. et al. Interleaved text\/image deep mining on a very large-scale radiology database. In Proc. 28th IEEE Conference on Computer Vision and Pattern Recognition 1090\u20131099 (IEEE, 2015).","DOI":"10.1109\/CVPR.2015.7298712"},{"key":"425_CR22","doi-asserted-by":"crossref","unstructured":"Wang, X. S., Peng, Y. F., Lu, L., Lu, Z. Y & Summers, R. M. Tienet: text-image embedding network for common thorax disease classification and reporting in chest X-rays. In Proc. 31st IEEE Conference on Computer Vision and Pattern Recognition 9049\u20139058 (IEEE, 2018).","DOI":"10.1109\/CVPR.2018.00943"},{"key":"425_CR23","doi-asserted-by":"crossref","unstructured":"Johnson, A. E. W. et al. MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs. Preprint at https:\/\/arxiv.org\/abs\/1901.07042 (2019).","DOI":"10.1038\/s41597-019-0322-0"},{"key":"425_CR24","unstructured":"Nguyen, H. Q. et al. VinDr-CXR: an open dataset of chest X-rays with radiologist\u2019s annotations. Preprint at https:\/\/arxiv.org\/abs\/2012.15029 (2021)."},{"key":"425_CR25","unstructured":"Jaeger, S. et al. Two public chest x-ray datasets for computer-aided screening of pulmonary diseases. Quant. Imaging Med. Surg. 4, 475 (2014)."},{"key":"425_CR26","unstructured":"Joseph, P. C. et al. COVID-19 Image Data Collection: prospective predictions are the future. Preprint at https:\/\/arxiv.org\/abs\/2006.11988 (2020)."},{"key":"425_CR27","doi-asserted-by":"crossref","unstructured":"Zhou, B.L., Khosla, A., Lapedriza, A., Oliva, A. & Torralba, A. Learning deep features for discriminative localization. In Proc. 29th IEEE Conference on Computer Vision and Pattern Recognition 2921\u20132929 (IEEE, 2016).","DOI":"10.1109\/CVPR.2016.319"},{"key":"425_CR28","unstructured":"Chetlur, S. et al. cuDNN: Efficient primitives for deep learning. Preprint at https:\/\/arxiv.org\/abs\/1410.0759 (2014)."},{"key":"425_CR29","doi-asserted-by":"crossref","unstructured":"He, K. M., Fan, H. Q., Wu, Y. X., Xie, S. N., & Girshick, R. Momentum contrast for unsupervised visual representation learning. In Proc. 33rd IEEE Conference on Computer Vision and Pattern Recognition 9729\u20139738 (IEEE, 2020).","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"425_CR30","unstructured":"Ba, J. L., Kiros, J. R. & Hinton, G. E. Layer normalization. In 4th International Conference on Learning Representations (ICLR, 2016)."},{"key":"425_CR31","doi-asserted-by":"crossref","unstructured":"Dahl, G.E., Sainath, T.N. & Hinton, G.E. Improving deep neural networks for LVCSR using rectified linear units and dropout. In Proc. 38th International Conference on Acoustics, Speech and Signal Processing 8609\u20138613 (IEEE, 2013).","DOI":"10.1109\/ICASSP.2013.6639346"},{"key":"425_CR32","unstructured":"Gutmann, M. & Hyv\u00e4rinen, A. Noise-contrastive estimation: a new estimation principle for unnormalized statistical models. In Proc. 13th International Conference on Artificial Intelligence and Statistics 297\u2013304 (JMLR, 2010)."},{"key":"425_CR33","unstructured":"Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proc. North American Chapter of the Association for Computational Linguistics: Human Language Technologies 4171\u20134186 (ACL, 2019)."},{"key":"425_CR34","unstructured":"Sutskever, I., Martens, J., Dahl, G. & Hinton, G.E. On the importance of initialization and momentum in deep learning. In Proc. 38th International Conference on Machine Learning 1139\u20131147 (PMLR, 2013)."},{"key":"425_CR35","doi-asserted-by":"crossref","unstructured":"Goyal, P., Mahajan, D., Gupta, A. & Misra, I. Scaling and benchmarking self-supervised visual representation learning. In Proc. 17th International Conference on Computer Vision 6391\u20136400 (IEEE, 2019).","DOI":"10.1109\/ICCV.2019.00649"},{"key":"425_CR36","unstructured":"Loshchilov, I. & Hutter, F. SGDR: stochastic gradient descent with warm restarts. In 5th International Conference on Learning Representations (ICLR, 2017)."},{"key":"425_CR37","unstructured":"Paszke, A. et al. PyTorch: an imperative style, high-performance deep learning library. In Proc. 33rd Advances in Neural Information Processing Systems 8024\u20138035 (2019)."},{"key":"425_CR38","unstructured":"Micikevicius, P. et al. Mixed precision training. In 6th International Conference on Learning Representations (ICLR, 2018)."},{"key":"425_CR39","unstructured":"Kingma, D. P. & Ba, J. L. Adam: a method for stochastic optimization. In 2nd International Conference on Learning Representations (ICLR, 2014)."},{"key":"425_CR40","doi-asserted-by":"publisher","unstructured":"Zhou, H.Y. et al. Generalized Radiograph Representation Learning via Cross-supervision between Images and Free-text Radiology Reports (Zenodo, 2021); https:\/\/doi.org\/10.5281\/zenodo.5624117","DOI":"10.5281\/zenodo.5624117"}],"container-title":["Nature Machine Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s42256-021-00425-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-021-00425-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-021-00425-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T17:10:29Z","timestamp":1733937029000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s42256-021-00425-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,20]]},"references-count":40,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,1]]}},"alternative-id":["425"],"URL":"https:\/\/doi.org\/10.1038\/s42256-021-00425-9","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2021.11.02.21265838","asserted-by":"object"}]},"ISSN":["2522-5839"],"issn-type":[{"value":"2522-5839","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,20]]},"assertion":[{"value":"22 June 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 November 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 January 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}