{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T10:56:22Z","timestamp":1768992982330,"version":"3.49.0"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2023,1,26]],"date-time":"2023-01-26T00:00:00Z","timestamp":1674691200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,1,26]],"date-time":"2023-01-26T00:00:00Z","timestamp":1674691200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100003710","name":"Korea Health Industry Development Institute","doi-asserted-by":"publisher","award":["HI18C2383"],"award-info":[{"award-number":["HI18C2383"]}],"id":[{"id":"10.13039\/501100003710","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Digit Imaging"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Training deep learning models on medical images heavily depends on experts\u2019 expensive and laborious manual labels. In addition, these images, labels, and even models themselves are not widely publicly accessible and suffer from various kinds of bias and imbalances. In this paper, chest X-ray pre-trained model via self-supervised contrastive learning (CheSS) was proposed to learn models with various representations in chest radiographs (CXRs). Our contribution is a publicly accessible pretrained model trained with a 4.8-M CXR dataset using self-supervised learning with a contrastive learning and its validation with various kinds of downstream tasks including classification on the 6-class diseases in internal dataset, diseases classification in CheXpert, bone suppression, and nodule generation. When compared to a scratch model, on the 6-class classification test dataset, we achieved 28.5% increase in accuracy. On the CheXpert dataset, we achieved 1.3% increase in mean area under the receiver operating characteristic curve on the full dataset and 11.4% increase only using 1% data in stress test manner. On bone suppression with perceptual loss, we achieved improvement in peak signal to noise ratio from 34.99 to 37.77, structural similarity index measure from 0.976 to 0.977, and root-square-mean error from 4.410 to 3.301 when compared to ImageNet pretrained model. Finally, on nodule generation, we achieved improvement in Fr\u00e9chet inception distance from 24.06 to 17.07. Our study showed the decent transferability of CheSS weights. CheSS weights can help researchers overcome data imbalance, data shortage, and inaccessibility of medical image datasets. CheSS weight is available at <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/mi2rl\/CheSS\">https:\/\/github.com\/mi2rl\/CheSS<\/jats:ext-link>.<\/jats:p>","DOI":"10.1007\/s10278-023-00782-4","type":"journal-article","created":{"date-parts":[[2023,1,26]],"date-time":"2023-01-26T21:02:53Z","timestamp":1674766973000},"page":"902-910","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["CheSS: Chest X-Ray Pre-trained Model via Self-supervised Contrastive Learning"],"prefix":"10.1007","volume":"36","author":[{"given":"Kyungjin","family":"Cho","sequence":"first","affiliation":[]},{"given":"Ki Duk","family":"Kim","sequence":"additional","affiliation":[]},{"given":"Yujin","family":"Nam","sequence":"additional","affiliation":[]},{"given":"Jiheon","family":"Jeong","sequence":"additional","affiliation":[]},{"given":"Jeeyoung","family":"Kim","sequence":"additional","affiliation":[]},{"given":"Changyong","family":"Choi","sequence":"additional","affiliation":[]},{"given":"Soyoung","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Jun Soo","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Seoyeon","family":"Woo","sequence":"additional","affiliation":[]},{"given":"Gil-Sun","family":"Hong","sequence":"additional","affiliation":[]},{"given":"Joon Beom","family":"Seo","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3438-2217","authenticated-orcid":false,"given":"Namkug","family":"Kim","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,1,26]]},"reference":[{"key":"782_CR1","doi-asserted-by":"crossref","unstructured":"P. Voigt, A. Von dem Bussche, The eu general data protection regulation (gdpr), A Practical Guide, 1st Ed., Cham: Springer International Publishing, 10 (2017) 10.5555.","DOI":"10.1007\/978-3-319-57959-7_1"},{"key":"782_CR2","doi-asserted-by":"publisher","first-page":"1486","DOI":"10.1056\/NEJMlim035027","volume":"348","author":"GJ Annas","year":"2003","unstructured":"G.J. Annas, HIPAA regulations: a new era of medical-record privacy?, New England Journal of Medicine, 348 (2003) 1486.","journal-title":"New England Journal of Medicine"},{"key":"782_CR3","doi-asserted-by":"publisher","first-page":"921","DOI":"10.1038\/nbt.3340","volume":"33","author":"LJ Kish","year":"2015","unstructured":"L.J. Kish, E.J. Topol, Unpatients\u2014why patients should own their medical data, Nature biotechnology, 33 (2015) 921-924.","journal-title":"Nature biotechnology"},{"key":"782_CR4","first-page":"69","volume-title":"Unsupervised learning of visual representations by solving jigsaw puzzles","author":"M Noroozi","year":"2016","unstructured":"M. Noroozi, P. Favaro, Unsupervised learning of visual representations by solving jigsaw puzzles, European conference on computer vision, Springer, 2016, pp. 69-84."},{"key":"782_CR5","unstructured":"A.v.d. Oord, Y. Li, O. Vinyals, Representation learning with contrastive predictive coding, arXiv preprint arXiv:1807.03748, (2018)."},{"key":"782_CR6","unstructured":"X. Chen, H. Fan, R. Girshick, K. He, Improved baselines with momentum contrastive learning, arXiv preprint arXiv:2003.04297, (2020)."},{"key":"782_CR7","unstructured":"T. Chen, S. Kornblith, M. Norouzi, G. Hinton, A simple framework for contrastive learning of visual representations, International conference on machine learning, PMLR, 2020, pp. 1597\u20131607."},{"key":"782_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101539","volume":"58","author":"L Chen","year":"2019","unstructured":"L. Chen, P. Bentley, K. Mori, K. Misawa, M. Fujiwara, D. Rueckert, Self-supervised learning for medical image analysis using image context restoration, Medical image analysis, 58 (2019) 101539.","journal-title":"Medical image analysis"},{"key":"782_CR9","doi-asserted-by":"crossref","unstructured":"S. Azizi, B. Mustafa, F. Ryan, Z. Beaver, J. Freyberg, J. Deaton, A. Loh, A. Karthikesalingam, S. Kornblith, T. Chen, Big self-supervised models advance medical image classification, arXiv preprint arXiv:2101.05224, (2021).","DOI":"10.1109\/ICCV48922.2021.00346"},{"key":"782_CR10","unstructured":"H. Sowrirajan, J. Yang, A.Y. Ng, P. Rajpurkar, Moco pretraining improves representation and transferability of chest x-ray models, Medical Imaging with Deep Learning, PMLR, 2021, pp. 728\u2013744."},{"key":"782_CR11","doi-asserted-by":"crossref","unstructured":"X. Wang, Y. Peng, L. Lu, Z. Lu, M. Bagheri, R.M. Summers, Chestx-ray8: Hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases, Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 2097\u20132106.","DOI":"10.1109\/CVPR.2017.369"},{"key":"782_CR12","doi-asserted-by":"crossref","unstructured":"J. Irvin, P. Rajpurkar, M. Ko, Y. Yu, S. Ciurea-Ilcus, C. Chute, H. Marklund, B. Haghgoo, R. Ball, K. Shpanskaya, Chexpert: A large chest radiograph dataset with uncertainty labels and expert comparison, Proceedings of the AAAI conference on artificial intelligence, 2019, pp. 590\u2013597.","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"782_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41597-019-0322-0","volume":"6","author":"AE Johnson","year":"2019","unstructured":"A.E. Johnson, T.J. Pollard, S.J. Berkowitz, N.R. Greenbaum, M.P. Lungren, C.-y. Deng, R.G. Mark, S. Horng, MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports, Scientific data, 6 (2019) 1-8.","journal-title":"Scientific data"},{"key":"782_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101797","volume":"66","author":"A Bustos","year":"2020","unstructured":"A. Bustos, A. Pertusa, J.-M. Salinas, M. de la Iglesia-Vay\u00e1, Padchest: a large chest x-ray image dataset with multi-label annotated reports, Medical image analysis, 66 (2020) 101797.","journal-title":"Medical image analysis"},{"key":"782_CR15","unstructured":"J.P. Cohen, J.D. Viviano, P. Bertin, P. Morrison, P. Torabian, M. Guarrera, M.P. Lungren, A. Chaudhari, R. Brooks, M. Hashir, TorchXRayVision: A library of chest X-ray datasets and models, arXiv preprint arXiv:2111.00595, (2021)."},{"key":"782_CR16","first-page":"248","volume":"2009","author":"J Deng","year":"2009","unstructured":"J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, L. Fei-Fei, Imagenet: a large-scale hierarchical image database, 2009 IEEE conference on computer vision and pattern recognition, Ieee, 2009, pp. 248-255.","journal-title":"Ieee"},{"key":"782_CR17","doi-asserted-by":"crossref","unstructured":"F.C. Ghesu, B. Georgescu, A. Mansoor, Y. Yoo, D. Neumann, P. Patel, R. Vishwanath, J.M. Balter, Y. Cao, S. Grbic, Self-supervised Learning from 100 million medical images, arXiv preprint arXiv:2201.01283, (2022).","DOI":"10.1117\/1.JMI.9.6.064503"},{"key":"782_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2020.103698","volume":"119","author":"C Muramatsu","year":"2020","unstructured":"C. Muramatsu, M. Nishio, T. Goto, M. Oiwa, T. Morita, M. Yakami, T. Kubo, K. Togashi, H. Fujita, Improving breast mass classification by shared data with domain transformation using a generative adversarial network, Computers in biology and medicine, 119 (2020) 103698.","journal-title":"Computers in biology and medicine"},{"key":"782_CR19","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2021.694815","volume":"4","author":"M Nishio","year":"2021","unstructured":"M. Nishio, K. Fujimoto, H. Matsuo, C. Muramatsu, R. Sakamoto, H. Fujita, Lung cancer segmentation with transfer learning: usefulness of a pretrained model constructed from an artificial dataset generated using a generative adversarial network, Frontiers in artificial intelligence, 4 (2021) 694815.","journal-title":"Frontiers in artificial intelligence"},{"key":"782_CR20","doi-asserted-by":"publisher","first-page":"151972","DOI":"10.1109\/ACCESS.2021.3125324","volume":"9","author":"M Gazda","year":"2021","unstructured":"M. Gazda, J. Plavka, J. Gazda, P. Drotar, Self-supervised deep convolutional neural network for chest X-ray classification, IEEE Access, 9 (2021) 151972-151982.","journal-title":"IEEE Access"},{"key":"782_CR21","doi-asserted-by":"publisher","first-page":"509","DOI":"10.2214\/ajr.143.3.509","volume":"143","author":"WJ Tuddenham","year":"1984","unstructured":"W.J. Tuddenham, Glossary of terms for thoracic radiology: recommendations of the Nomenclature Committee of the Fleischner Society, American Journal of Roentgenology, 143 (1984) 509-517.","journal-title":"American Journal of Roentgenology"},{"key":"782_CR22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-018-37186-2","volume":"9","author":"B Park","year":"2019","unstructured":"B. Park, Y. Cho, G. Lee, S.M. Lee, Y.-H. Cho, E.S. Lee, K.H. Lee, J.B. Seo, N. Kim, A curriculum learning strategy to enhance the accuracy of classification of various lesions in chest-PA X-ray screening for pulmonary abnormalities, Scientific reports, 9 (2019) 1-9.","journal-title":"Scientific reports"},{"key":"782_CR23","doi-asserted-by":"crossref","unstructured":"Z. Yuan, Y. Yan, M. Sonka, T. Yang, Large-scale robust deep AUC maximization: a new surrogate loss and empirical studies on medical image classification, arXiv preprint arXiv:2012.03173, (2020).","DOI":"10.1109\/ICCV48922.2021.00303"},{"key":"782_CR24","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1016\/j.neucom.2020.03.127","volume":"437","author":"HH Pham","year":"2021","unstructured":"H.H. Pham, T.T. Le, D.Q. Tran, D.T. Ngo, H.Q. Nguyen, Interpreting chest X-rays via CNNs that exploit hierarchical disease dependencies and uncertainty labels, Neurocomputing, 437 (2021) 186-194.","journal-title":"Neurocomputing"},{"key":"782_CR25","doi-asserted-by":"crossref","unstructured":"G.-S. Hong, K.-H. Do, C.W. Lee, Added value of bone suppression image in the detection of subtle lung lesions on chest radiographs with regard to reader\u2019s expertise, Journal of Korean medical science, 34 (2019).","DOI":"10.3346\/jkms.2019.34.e250"},{"key":"782_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2022.106705","volume":"220","author":"KD Kim","year":"2022","unstructured":"K.D. Kim, K. Cho, M. Kim, K.H. Lee, S. Lee, S.M. Lee, K.H. Lee, N. Kim, Enhancing deep learning based classifiers with inpainting anatomical side markers (L\/R markers) for multi-center trials, Computer Methods and Programs in Biomedicine, 220 (2022) 106705.","journal-title":"Computer Methods and Programs in Biomedicine"},{"key":"782_CR27","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"782_CR28","doi-asserted-by":"crossref","unstructured":"K. He, H. Fan, Y. Wu, S. Xie, R. Girshick, Momentum contrast for unsupervised visual representation learning, Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 2020, pp. 9729\u20139738.","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"782_CR29","doi-asserted-by":"publisher","first-page":"2289","DOI":"10.1109\/TMI.2020.2968472","volume":"39","author":"M Li","year":"2020","unstructured":"M. Li, W. Hsu, X. Xie, J. Cong, W. Gao, SACNN: Self-attention convolutional neural network for low-dose CT denoising with self-supervised perceptual loss network, IEEE transactions on medical imaging, 39 (2020) 2289-2301.","journal-title":"IEEE transactions on medical imaging"},{"key":"782_CR30","unstructured":"H. Wei, F. Schiffers, T. W\u00fcrfl, D. Shen, D. Kim, A.K. Katsaggelos, O. Cossairt, 2-step sparse-view ct reconstruction with a domain-specific perceptual network, arXiv preprint arXiv:2012.04743, (2020)."},{"key":"782_CR31","doi-asserted-by":"publisher","first-page":"3555","DOI":"10.1002\/mp.13626","volume":"46","author":"J Ouyang","year":"2019","unstructured":"J. Ouyang, K.T. Chen, E. Gong, J. Pauly, G. Zaharchuk, Ultra\u2010low\u2010dose PET reconstruction using generative adversarial network with feature matching and task\u2010specific perceptual loss, Medical physics, 46 (2019) 3555-3564.","journal-title":"Medical physics"},{"key":"782_CR32","first-page":"694","volume-title":"Perceptual losses for real-time style transfer and super-resolution","author":"J Johnson","year":"2016","unstructured":"J. Johnson, A. Alahi, L. Fei-Fei, Perceptual losses for real-time style transfer and super-resolution, European conference on computer vision, Springer, 2016, pp. 694-711."},{"key":"782_CR33","unstructured":"M. Raghu, C. Zhang, J. Kleinberg, S. Bengio, Transfusion: understanding transfer learning for medical imaging, Advances in neural information processing systems, 32 (2019)."},{"key":"782_CR34","doi-asserted-by":"crossref","unstructured":"R.R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, D. Batra, Grad-cam: Visual explanations from deep networks via gradient-based localization, Proceedings of the IEEE international conference on computer vision, 2017, pp. 618\u2013626.","DOI":"10.1109\/ICCV.2017.74"},{"key":"782_CR35","doi-asserted-by":"crossref","unstructured":"O. Ronneberger, P. Fischer, T. Brox, U-net: Convolutional networks for biomedical image segmentation, International Conference on Medical image computing and computer-assisted intervention, Springer, 2015, pp. 234\u2013241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"782_CR36","unstructured":"F. Yu, V. Koltun, Multi-scale context aggregation by dilated convolutions, arXiv preprint arXiv:1511.07122, (2015)."},{"key":"782_CR37","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Z. Wang, A.C. Bovik, H.R. Sheikh, E.P. Simoncelli, Image quality assessment: from error visibility to structural similarity, IEEE transactions on image processing, 13 (2004) 600-612.","journal-title":"IEEE transactions on image processing"},{"key":"782_CR38","doi-asserted-by":"crossref","unstructured":"T. Park, M.-Y. Liu, T.-C. Wang, J.-Y. Zhu, Semantic image synthesis with spatially-adaptive normalization, Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 2019, pp. 2337\u20132346.","DOI":"10.1109\/CVPR.2019.00244"},{"key":"782_CR39","unstructured":"I.J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, Y. Bengio, Generative adversarial networks, arXiv preprint arXiv:1406.2661, (2014)."},{"key":"782_CR40","unstructured":"M. Heusel, H. Ramsauer, T. Unterthiner, B. Nessler, S. Hochreiter, Gans trained by a two time-scale update rule converge to a local nash equilibrium, Advances in neural information processing systems, 30 (2017)."}],"container-title":["Journal of Digital Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10278-023-00782-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10278-023-00782-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10278-023-00782-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,23]],"date-time":"2023-06-23T10:04:22Z","timestamp":1687514662000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10278-023-00782-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,26]]},"references-count":40,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2023,6]]}},"alternative-id":["782"],"URL":"https:\/\/doi.org\/10.1007\/s10278-023-00782-4","relation":{},"ISSN":["1618-727X"],"issn-type":[{"value":"1618-727X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,26]]},"assertion":[{"value":"14 November 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 January 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 January 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 January 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This retrospective study was conducted according to the principles of the Declaration of Helsinki and according to current scientific guidelines. The study protocol was approved by the Institutional Review Board Committee of Asan Medical Center, University of Ulsan College of Medicine, Seoul, Korea (IRB no.2019\u20130115). The requirement for informed patient consent was waived by the Institutional Review Board Committee of Asan Medical Center. The institutional review board approved this study (IRB number: 2019\u20130321), and the requirement for patient informed consent was waived owing to the retrospective nature of the study. This requirement for written informed consent was waived because the data were analyzed retrospectively and anonymously.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics Approval"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}}]}}