{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T00:48:12Z","timestamp":1772239692562,"version":"3.50.1"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,2,15]],"date-time":"2021-02-15T00:00:00Z","timestamp":1613347200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,2,15]],"date-time":"2021-02-15T00:00:00Z","timestamp":1613347200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000002","name":"U.S. Department of Health & Human Services | National Institutes of Health","doi-asserted-by":"publisher","award":["R01 grant EB017205"],"award-info":[{"award-number":["R01 grant EB017205"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"U.S. Department of Health & Human Services | National Institutes of Health","doi-asserted-by":"publisher","award":["R01 grant EB017205"],"award-info":[{"award-number":["R01 grant EB017205"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010629","name":"Fulbright Association","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010629","id-type":"DOI","asserted-by":"publisher"}]},{"name":"U.S. Department of Health & Human Services | National Institutes of Health"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Image-based teleconsultation using smartphones has become increasingly popular. In parallel, deep learning algorithms have been developed to detect radiological findings in chest X-rays (CXRs). However, the feasibility of using smartphones to automate this process has yet to be evaluated. This study developed a recalibration method to build deep learning models to detect radiological findings on CXR photographs. Two publicly available databases (MIMIC-CXR and CheXpert) were used to build the models, and four derivative datasets containing 6453 CXR photographs were collected to evaluate model performance. After recalibration, the model achieved areas under the receiver operating characteristic curve of 0.80 (95% confidence interval: 0.78\u20130.82), 0.88 (0.86\u20130.90), 0.81 (0.79\u20130.84), 0.79 (0.77\u20130.81), 0.84 (0.80\u20130.88), and 0.90 (0.88\u20130.92), respectively, for detecting cardiomegaly, edema, consolidation, atelectasis, pneumothorax, and pleural effusion. The recalibration strategy, respectively, recovered 84.9%, 83.5%, 53.2%, 57.8%, 69.9%, and 83.0% of performance losses of the uncalibrated model. We conclude that the recalibration method can transfer models from digital CXRs to CXR photographs, which is expected to help physicians\u2019 clinical works.<\/jats:p>","DOI":"10.1038\/s41746-021-00393-9","type":"journal-article","created":{"date-parts":[[2021,2,17]],"date-time":"2021-02-17T14:31:41Z","timestamp":1613572301000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Recalibration of deep learning models for abnormality detection in smartphone-captured chest radiograph"],"prefix":"10.1038","volume":"4","author":[{"given":"Po-Chih","family":"Kuo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng Che","family":"Tsai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9425-4375","authenticated-orcid":false,"given":"Diego M.","family":"L\u00f3pez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexandros","family":"Karargyris","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tom J.","family":"Pollard","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alistair E. W.","family":"Johnson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6712-6626","authenticated-orcid":false,"given":"Leo Anthony","family":"Celi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,2,15]]},"reference":[{"key":"393_CR1","doi-asserted-by":"publisher","first-page":"418","DOI":"10.1148\/radiol.2020192256","volume":"295","author":"FA Mettler Jr.","year":"2020","unstructured":"Mettler, F. A. Jr. et al. Patient exposure from radiologic and nuclear medicine procedures in the United States: procedure volume and effective dose for the period 2006-2016. Radiology 295, 418\u2013427 (2020).","journal-title":"Radiology"},{"key":"393_CR2","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1148\/radiol.2015150921","volume":"279","author":"AB Rosenkrantz","year":"2016","unstructured":"Rosenkrantz, A. B., Hughes, D. R. & Richard Duszak, J. The U.S. radiologist workforce: an analysis of temporal and geographic variation by using large national datasets. Radiology 279, 175\u2013184 (2016).","journal-title":"Radiology"},{"key":"393_CR3","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1136\/emermed-2015-205258","volume":"34","author":"C Boissin","year":"2017","unstructured":"Boissin, C., Blom, L., Wallis, L. & Laflamme, L. Image-based teleconsultation using smartphones or tablets: qualitative assessment of medical experts. Emerg. Med. J. 34, 95\u201399 (2017).","journal-title":"Emerg. Med. J."},{"key":"393_CR4","doi-asserted-by":"publisher","first-page":"19","DOI":"10.21037\/mhealth.2019.11.01","volume":"6","author":"D Giansanti","year":"2020","unstructured":"Giansanti, D. WhatsApp in mHealth: an overview on the potentialities and the opportunities in medical imaging. Mhealth 6, 19\u201319 (2020).","journal-title":"Mhealth"},{"key":"393_CR5","doi-asserted-by":"publisher","first-page":"997","DOI":"10.2214\/AJR.18.20771","volume":"212","author":"WF Auffermann","year":"2019","unstructured":"Auffermann, W. F., Gozansky, E. K. & Tridandapani, S. Artificial intelligence in cardiothoracic radiology. Am. J. Roentgenol. 212, 997\u20131001 (2019).","journal-title":"Am. J. Roentgenol."},{"key":"393_CR6","doi-asserted-by":"publisher","first-page":"1472","DOI":"10.1016\/j.acra.2018.02.018","volume":"25","author":"MP McBee","year":"2018","unstructured":"McBee, M. P. et al. Deep learning in radiology. Academic Radiol. 25, 1472\u20131480 (2018).","journal-title":"Academic Radiol."},{"key":"393_CR7","unstructured":"Rajpurkar, P. et al. Chexnet: radiologist-level pneumonia detection on chest x-rays with deep learning. Preprint at https:\/\/arxiv.org\/abs\/1711.05225 (2017)."},{"key":"393_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-019-42294-8","volume":"9","author":"IM Baltruschat","year":"2019","unstructured":"Baltruschat, I. M., Nickisch, H., Grass, M., Knopp, T. & Saalbach, A. Comparison of deep learning approaches for multi-label chest X-ray classification. Sci. Rep. 9, 1\u201310 (2019).","journal-title":"Sci. Rep."},{"key":"393_CR9","doi-asserted-by":"publisher","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 Medicine 15, https:\/\/doi.org\/10.1371\/journal.pmed.1002697 (2018).","DOI":"10.1371\/journal.pmed.1002697"},{"key":"393_CR10","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1148\/radiol.2018180921","volume":"291","author":"M Annarumma","year":"2019","unstructured":"Annarumma, M. et al. Automated triaging of adult chest radiographs with deep artificial neural networks. Radiology 291, 196\u2013202 (2019).","journal-title":"Radiology"},{"key":"393_CR11","doi-asserted-by":"publisher","first-page":"e1002686","DOI":"10.1371\/journal.pmed.1002686","volume":"15","author":"P Rajpurkar","year":"2018","unstructured":"Rajpurkar, P. et al. Deep learning for chest radiograph diagnosis: a retrospective comparison of the CheXNeXt algorithm to practicing radiologists. PLoS Med. 15, e1002686 (2018).","journal-title":"PLoS Med."},{"key":"393_CR12","first-page":"2097","volume":"2017","author":"X Wang","year":"2017","unstructured":"Wang, X. et al. ChestX-ray8: hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. Proc. IEEE Conf. Computer Vis. Pattern Recognit. 2017, 2097\u20132106 (2017).","journal-title":"Proc. IEEE Conf. Computer Vis. Pattern Recognit."},{"key":"393_CR13","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1148\/radiol.2019191293","volume":"294","author":"A Majkowska","year":"2020","unstructured":"Majkowska, A. et al. Chest radiograph interpretation with deep learning models: Assessment with radiologist-adjudicated reference standards and population-adjusted evaluation. Radiology 294, 421\u2013431 (2020).","journal-title":"Radiology"},{"key":"393_CR14","doi-asserted-by":"publisher","first-page":"218","DOI":"10.1148\/radiol.2018180237","volume":"290","author":"JG Nam","year":"2019","unstructured":"Nam, J. G. et al. Development and validation of deep learning\u2013based automatic detection algorithm for malignant pulmonary nodules on chest radiographs. Radiology 290, 218\u2013228 (2019).","journal-title":"Radiology"},{"key":"393_CR15","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1148\/radiol.2017162326","volume":"284","author":"P Lakhani","year":"2017","unstructured":"Lakhani, P. & Sundaram, B. Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks. Radiology 284, 574\u2013582 (2017).","journal-title":"Radiology"},{"key":"393_CR16","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-0273-z","volume":"3","author":"Y-X Tang","year":"2020","unstructured":"Tang, Y.-X. et al. Automated abnormality classification of chest radiographs using deep convolutional neural networks. npj Digital Med. 3, 70 (2020).","journal-title":"npj Digital Med."},{"key":"393_CR17","first-page":"757","volume":"11401","author":"S G\u00fcndel","year":"2019","unstructured":"G\u00fcndel, S. et al. Learning to recognize abnormalities in chest X-rays with location-aware dense networks. Prog. Pattern Recognit. Image Anal. Computer Vis. Appl. 11401, 757\u2013765 (2019).","journal-title":"Prog. Pattern Recognit. Image Anal. Computer Vis. Appl."},{"key":"393_CR18","first-page":"590","volume":"33","author":"J Irvin","year":"2019","unstructured":"Irvin, J. et al. CheXpert: a large chest radiograph dataset with uncertainty labels and expert comparison. Proc. AAAI Conf. Artif. Intell. 33, 590\u2013597 (2019).","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"393_CR19","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0","volume":"6","author":"AEW Johnson","year":"2019","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, 317 (2019).","journal-title":"Sci. Data"},{"key":"393_CR20","first-page":"618","volume":"2017","author":"RR Selvaraju","year":"2017","unstructured":"Selvaraju, R. R. et al. Grad-CAM: visual explanations from deep networks via gradient-based localization. Proc. IEEE Int. Conf. Computer Vis. 2017, 618\u2013626 (2017).","journal-title":"Proc. IEEE Int. Conf. Computer Vis."},{"key":"393_CR21","unstructured":"Kurakin, A., Goodfellow, I. & Bengio, S. Adversarial examples in the physical world. Proc. Workshop Int. Conf. Learn. Represent. 2017, 1\u201311 (2016)."},{"key":"393_CR22","doi-asserted-by":"publisher","unstructured":"Zech, J. R. et al. Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: a cross-sectional study. PLoS Medicine 15, https:\/\/doi.org\/10.1371\/journal.pmed.1002683 (2018).","DOI":"10.1371\/journal.pmed.1002683"},{"key":"393_CR23","doi-asserted-by":"crossref","unstructured":"Pooch, E. H., Ballester, P. L. & Barros, R. C. Can we trust deep learning models diagnosis? The impact of domain shift in chest radiograph classification. In Proc. of Machine Learning Research 121, 136\u2013155 (2020).","DOI":"10.1007\/978-3-030-62469-9_7"},{"key":"393_CR24","unstructured":"Rajpurkar, P. et al. CheXpedition: Investigating generalization challenges for translation of chest X-ray algorithms to the clinical setting. Preprint at https:\/\/arxiv.org\/abs\/2002.11379 (2020)."},{"key":"393_CR25","unstructured":"Phillips, N. A. et al. CheXphoto: 10,000+ smartphone photos and synthetic photographic transformations of chest X-rays for benchmarking deep learning robustness. In Proc. of Machine Learning Research 136, 318\u2013327 (2020)."},{"key":"393_CR26","doi-asserted-by":"publisher","DOI":"10.1007\/s40134-019-0336-6","volume":"7","author":"DA Rosman","year":"2019","unstructured":"Rosman, D. A., Bamporiki, J., Stein-Wexler, R. & Harris, R. D. Developing diagnostic radiology training in low resource countries. Curr. Radiol. Rep. 7, 27 (2019).","journal-title":"Curr. Radiol. Rep."},{"key":"393_CR27","first-page":"188","volume":"2018","author":"Y Peng","year":"2018","unstructured":"Peng, Y. et al. Negbio: a high-performance tool for negation and uncertainty detection in radiology reports. AMIA Summits Transl. Sci. Proc. 2018, 188 (2018).","journal-title":"AMIA Summits Transl. Sci. Proc."},{"key":"393_CR28","doi-asserted-by":"crossref","unstructured":"Boncelet, C. In The Essential Guide to Image Processing (ed Al Bovik) 143\u2013167 (Academic Press, 2009).","DOI":"10.1016\/B978-0-12-374457-9.00007-X"},{"key":"393_CR29","unstructured":"Jung, A. imgaug (2017) https:\/\/github.com\/aleju\/imgaug (2019)."},{"key":"393_CR30","unstructured":"Deans, S. R. The Radon Transform and Some of its Applications (Courier Corporation, 2007)."},{"key":"393_CR31","doi-asserted-by":"publisher","first-page":"2163","DOI":"10.1364\/OE.20.002163","volume":"20","author":"V Saveljev","year":"2012","unstructured":"Saveljev, V. & Kim, S.-K. Simulation and measurement of moir\u00e9 patterns at finite distance. Opt. Express 20, 2163\u20132177 (2012).","journal-title":"Opt. Express"},{"key":"393_CR32","doi-asserted-by":"publisher","first-page":"e453","DOI":"10.7717\/peerj.453","volume":"2","author":"S Van der Walt","year":"2014","unstructured":"Van der Walt, S. et al. scikit-image: image processing in Python. PeerJ 2, e453 (2014).","journal-title":"PeerJ"},{"key":"393_CR33","doi-asserted-by":"publisher","first-page":"2385","DOI":"10.1109\/TIP.2009.2025923","volume":"18","author":"MP Sampat","year":"2009","unstructured":"Sampat, M. P., Wang, Z., Gupta, S., Bovik, A. C. & Markey, M. K. Complex wavelet structural similarity: a new image similarity index. IEEE Trans. image Process. 18, 2385\u20132401 (2009).","journal-title":"IEEE Trans. image Process."},{"key":"393_CR34","first-page":"4700","volume":"2017","author":"G Huang","year":"2017","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L. & Weinberger, K. Q. Densely connectedconvolutional networks In Proc. IEEE Conf. Computer Vis. Pattern Recognit 2017, 4700\u20134708 (2017).","journal-title":"Proc. IEEE Conf. Computer Vis. Pattern Recognit"},{"key":"393_CR35","doi-asserted-by":"crossref","unstructured":"Seyyed-Kalantari, L., Liu, G., McDermott, M. & Ghassemi, M. CheXclusion: Fairness gaps in deep chest X-ray classifiers. Preprint at https:\/\/arxiv.org\/abs\/2003.00827 (2020).","DOI":"10.1142\/9789811232701_0022"},{"key":"393_CR36","first-page":"e190015","volume":"2","author":"CF Sabottke","year":"2020","unstructured":"Sabottke, C. F. & Spieler, B. M. The effect of image resolution on deep learning in radiography. Radiology: Artif. Intell. 2, e190015 (2020).","journal-title":"Radiology: Artif. Intell."},{"key":"393_CR37","unstructured":"Kingma, D. P. & Ba, J. Adam: A method for stochastic optimization. Preprint at https:\/\/arxiv.org\/abs\/1412.6980 (2014)."},{"key":"393_CR38","doi-asserted-by":"crossref","unstructured":"Pham, H. H., Le, T. T., Tran, D. Q., Ngo, D. T. & Nguyen, H. Q. Interpreting chest X-rays via CNNs that exploit disease dependencies and uncertainty labels. Preprint at https:\/\/arxiv.org\/abs\/1911.06475 (2019).","DOI":"10.1101\/19013342"}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-021-00393-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-021-00393-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-021-00393-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,3]],"date-time":"2022-12-03T19:13:33Z","timestamp":1670094813000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-021-00393-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,15]]},"references-count":38,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["393"],"URL":"https:\/\/doi.org\/10.1038\/s41746-021-00393-9","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2,15]]},"assertion":[{"value":"6 July 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 January 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 February 2021","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"}}],"article-number":"25"}}