{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T16:01:20Z","timestamp":1792598480644,"version":"4.5.0"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,1,2]],"date-time":"2025-01-02T00:00:00Z","timestamp":1735776000000},"content-version":"vor","delay-in-days":1,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Med"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Ovarian lesions are common and often incidentally detected. A critical shortage of expert ultrasound examiners has raised concerns of unnecessary interventions and delayed cancer diagnoses. Deep learning has shown promising results in the detection of ovarian cancer in ultrasound images; however, external validation is lacking. In this international multicenter retrospective study, we developed and validated transformer-based neural network models using a comprehensive dataset of 17,119 ultrasound images from 3,652 patients across 20 centers in eight countries. Using a leave-one-center-out cross-validation scheme, for each center in turn, we trained a model using data from the remaining centers. The models demonstrated robust performance across centers, ultrasound systems, histological diagnoses and patient age groups, significantly outperforming both expert and non-expert examiners on all evaluated metrics, namely F1 score, sensitivity, specificity, accuracy, Cohen\u2019s kappa, Matthew\u2019s correlation coefficient, diagnostic odds ratio and Youden\u2019s J statistic. Furthermore, in a retrospective triage simulation, artificial intelligence (AI)-driven diagnostic support reduced referrals to experts by 63% while significantly surpassing the diagnostic performance of the current practice. These results show that transformer-based models exhibit strong generalization and above human expert-level diagnostic accuracy, with the potential to alleviate the shortage of expert ultrasound examiners and improve patient outcomes.<\/jats:p>","DOI":"10.1038\/s41591-024-03329-4","type":"journal-article","created":{"date-parts":[[2025,1,2]],"date-time":"2025-01-02T05:04:30Z","timestamp":1735794270000},"page":"189-196","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":67,"title":["International multicenter validation of AI-driven ultrasound detection of ovarian cancer"],"prefix":"10.1038","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7206-9611","authenticated-orcid":false,"given":"Filip","family":"Christiansen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9437-4553","authenticated-orcid":false,"given":"Emir","family":"Konuk","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8216-6458","authenticated-orcid":false,"given":"Adithya Raju","family":"Ganeshan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1819-6120","authenticated-orcid":false,"given":"Robert","family":"Welch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4117-1638","authenticated-orcid":false,"given":"Joana","family":"Pal\u00e9s Huix","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Artur","family":"Czekierdowski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francesco Paolo Giuseppe","family":"Leone","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5749-7968","authenticated-orcid":false,"given":"Lucia Anna","family":"Haak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5688-2194","authenticated-orcid":false,"given":"Robert","family":"Fruscio","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adrius","family":"Gaurilcikas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3950-5538","authenticated-orcid":false,"given":"Dorella","family":"Franchi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7224-3218","authenticated-orcid":false,"given":"Daniela","family":"Fischerova","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elisa","family":"Mor","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Savelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5095-6981","authenticated-orcid":false,"given":"Maria \u00c0ngela","family":"Pascual","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marek Jerzy","family":"Kudla","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefano","family":"Guerriero","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6587-2622","authenticated-orcid":false,"given":"Francesca","family":"Buonomo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karina","family":"Liuba","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nina","family":"Montik","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan Luis","family":"Alc\u00e1zar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8899-3040","authenticated-orcid":false,"given":"Ekaterini","family":"Domali","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nelinda Catherine P.","family":"Pangilinan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2690-5686","authenticated-orcid":false,"given":"Chiara","family":"Carella","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maria","family":"Munaretto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5367-8056","authenticated-orcid":false,"given":"Petra","family":"Saskova","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7406-8804","authenticated-orcid":false,"given":"Debora","family":"Verri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chiara","family":"Visenzi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pawel","family":"Herman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kevin","family":"Smith","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2298-7785","authenticated-orcid":false,"given":"Elisabeth","family":"Epstein","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,1,2]]},"reference":[{"key":"3329_CR1","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1016\/S1470-2045(08)70005-6","volume":"9","author":"J Yazbek","year":"2008","unstructured":"Yazbek, J. et al. Effect of quality of gynaecological ultrasonography on management of patients with suspected ovarian cancer: a randomised controlled trial. Lancet Oncol. 9, 124\u2013131 (2008).","journal-title":"Lancet Oncol."},{"key":"3329_CR2","doi-asserted-by":"publisher","first-page":"448","DOI":"10.1016\/S1470-2045(18)30837-4","volume":"20","author":"W Froyman","year":"2019","unstructured":"Froyman, W. et al. Risk of complications in patients with conservatively managed ovarian tumours (IOTA5): a 2-year interim analysis of a multicentre, prospective, cohort study. Lancet Oncol. 20, 448\u2013458 (2019).","journal-title":"Lancet Oncol."},{"key":"3329_CR3","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1016\/S0140-6736(00)03590-X","volume":"357","author":"I Vergote","year":"2001","unstructured":"Vergote, I. et al. Prognostic importance of degree of differentiation and cyst rupture in stage I invasive epithelial ovarian carcinoma. Lancet 357, 176\u2013182 (2001).","journal-title":"Lancet"},{"key":"3329_CR4","doi-asserted-by":"publisher","first-page":"4065","DOI":"10.1200\/JCO.22.02765","volume":"41","author":"RE Bristow","year":"2023","unstructured":"Bristow, R. E., Tomacruz, R. S., Armstrong, D. K., Trimble, E. L. & Montz, F. J. Survival effect of maximal cytoreductive surgery for advanced ovarian carcinoma during the platinum era: a meta-analysis. J. Clin. Oncol. 41, 4065\u20134076 (2023).","journal-title":"J. Clin. Oncol."},{"key":"3329_CR5","doi-asserted-by":"publisher","first-page":"961","DOI":"10.1136\/ijgc-2021-002565","volume":"31","author":"D Timmerman","year":"2021","unstructured":"Timmerman, D. et al. ESGO\/ISUOG\/IOTA\/ESGE Consensus Statement on pre-operative diagnosis of ovarian tumors. Int. J. Gynecol. Cancer 31, 961\u2013982 (2021).","journal-title":"Int. J. Gynecol. Cancer"},{"key":"3329_CR6","doi-asserted-by":"publisher","first-page":"454","DOI":"10.1002\/uog.6443","volume":"34","author":"C Van Holsbeke","year":"2009","unstructured":"Van Holsbeke, C. et al. Ultrasound methods to distinguish between malignant and benign adnexal masses in the hands of examiners with different levels of experience. Ultrasound Obstet. Gynecol. 34, 454\u2013461 (2009).","journal-title":"Ultrasound Obstet. Gynecol."},{"key":"3329_CR7","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1159\/000265012","volume":"69","author":"C Van Holsbeke","year":"2010","unstructured":"Van Holsbeke, C. et al. Ultrasound experience substantially impacts on diagnostic performance and confidence when adnexal masses are classified using pattern recognition. Gynecol. Obstet. Invest. 69, 160\u2013168 (2010).","journal-title":"Gynecol. Obstet. Invest."},{"key":"3329_CR8","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1046\/j.1469-0705.1999.13010011.x","volume":"13","author":"D Timmerman","year":"1999","unstructured":"Timmerman, D. et al. Subjective assessment of adnexal masses with the use of ultrasonography: an analysis of interobserver variability and experience. Ultrasound Obstet. Gynecol. 13, 11\u201316 (1999).","journal-title":"Ultrasound Obstet. Gynecol."},{"key":"3329_CR9","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1002\/uog.23530","volume":"57","author":"F Christiansen","year":"2021","unstructured":"Christiansen, F. et al. Ultrasound image analysis using deep neural networks for discriminating between benign and malignant ovarian tumors: comparison with expert subjective assessment. Ultrasound Obstet. Gynecol. 57, 155\u2013163 (2021).","journal-title":"Ultrasound Obstet. Gynecol."},{"key":"3329_CR10","doi-asserted-by":"publisher","first-page":"e179","DOI":"10.1016\/S2589-7500(21)00278-8","volume":"4","author":"Y Gao","year":"2022","unstructured":"Gao, Y. et al. Deep learning-enabled pelvic ultrasound images for accurate diagnosis of ovarian cancer in China: a retrospective, multicentre, diagnostic study. Lancet Digit. Health 4, e179\u2013e187 (2022).","journal-title":"Lancet Digit. Health"},{"key":"3329_CR11","doi-asserted-by":"publisher","first-page":"e1391","DOI":"10.1503\/cmaj.202066","volume":"193","author":"JP Cohen","year":"2021","unstructured":"Cohen, J. P. et al. Problems in the deployment of machine-learned models in health care. CMAJ 193, e1391\u2013e1394 (2021).","journal-title":"CMAJ"},{"key":"3329_CR12","unstructured":"Goodfellow, I., Bengio, Y. & Courville, A. Deep Learning (MIT Press, 2016)."},{"key":"3329_CR13","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1109\/JBHI.2020.3032060","volume":"25","author":"K Stacke","year":"2020","unstructured":"Stacke, K. et al. Measuring domain shift for deep learning in histopathology. IEEE J. Biomed. Health Inform. 25, 325\u2013336 (2020).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"3329_CR14","doi-asserted-by":"crossref","unstructured":"Sharifzadeh, M., Tehrani, A. K., Benali, H. & Rivaz, H. Ultrasound domain adaptation using frequency domain analysis. 2021 IEEE International Ultrasonics Symposium (IUS), 1\u20134 (2021).","DOI":"10.1109\/IUS52206.2021.9593856"},{"key":"3329_CR15","doi-asserted-by":"crossref","unstructured":"Tierney, J., et al. Accounting for domain shift in neural network ultrasound beamforming. 2020 IEEE International Ultrasonics Symposium (IUS), 1\u20133 (2020).","DOI":"10.1109\/IUS46767.2020.9251577"},{"key":"3329_CR16","doi-asserted-by":"publisher","first-page":"e271","DOI":"10.1016\/S2589-7500(19)30123-2","volume":"1","author":"X Liu","year":"2019","unstructured":"Liu, X. et al. A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis. Lancet Digit. Health 1, e271\u2013e297 (2019).","journal-title":"Lancet Digit. Health"},{"key":"3329_CR17","doi-asserted-by":"publisher","first-page":"e899","DOI":"10.1016\/S2589-7500(22)00186-8","volume":"4","author":"A Chalkidou","year":"2022","unstructured":"Chalkidou, A. et al. Recommendations for the development and use of imaging test sets to investigate the test performance of artificial intelligence in health screening. Lancet Digit. Health 4, e899\u2013e905 (2022).","journal-title":"Lancet Digit. Health"},{"key":"3329_CR18","doi-asserted-by":"publisher","DOI":"10.1186\/s12916-019-1426-2","volume":"17","author":"CJ Kelly","year":"2019","unstructured":"Kelly, C. J., Karthikesalingam, A., Suleyman, M., Corrado, G. & King, D. Key challenges for delivering clinical impact with artificial intelligence. BMC Med. 17, 195 (2019).","journal-title":"BMC Med."},{"key":"3329_CR19","unstructured":"Dosovitskiy, A. et al. An image is worth 16x16 words: transformers for image recognition at scale. International Conference on Learning Representations (2020)."},{"key":"3329_CR20","doi-asserted-by":"crossref","unstructured":"Touvron, H., Cord, M. & J\u00e9gou, H. DeiT III: Revenge of the ViT. 17th European Conference on Computer Vision, 516\u2013533 (2022).","DOI":"10.1007\/978-3-031-20053-3_30"},{"key":"3329_CR21","doi-asserted-by":"crossref","unstructured":"Matsoukas, C., Haslum, J. F., Sorkhei, M., S\u00f6derberg, M. & Smith, K. What makes transfer learning work for medical images: feature reuse & other factors. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 9225\u20139234 (2022).","DOI":"10.1109\/CVPR52688.2022.00901"},{"key":"3329_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102802","volume":"88","author":"F Shamshad","year":"2023","unstructured":"Shamshad, F. et al. Transformers in medical imaging: a survey. Med. Image Anal. 88, 102802 (2023).","journal-title":"Med. Image Anal."},{"key":"3329_CR23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12916-019-1466-7","volume":"17","author":"B Van Calster","year":"2019","unstructured":"Van Calster, B. et al. Calibration: The Achilles heel of predictive analytics. BMC Med. 17, 1\u20137 (2019).","journal-title":"BMC Med."},{"key":"3329_CR24","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1016\/j.jclinepi.2015.12.005","volume":"74","author":"B Van Calster","year":"2016","unstructured":"Van Calster, B. et al. A calibration hierarchy for risk models was defined: from utopia to empirical data. J. Clin. Epidemiol. 74, 167\u2013176 (2016).","journal-title":"J. Clin. Epidemiol."},{"key":"3329_CR25","doi-asserted-by":"crossref","unstructured":"Caron, M., et al. Emerging properties in self-supervised vision transformers. Proceedings of the IEEE\/CVF International Conference on Computer Vision, 9650\u20139660 (2021).","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"3329_CR26","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R. & Farhadi, A. You only look once: unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 779\u2013788 (2016).","DOI":"10.1109\/CVPR.2016.91"},{"key":"3329_CR27","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1214\/ss\/1009213286","volume":"16","author":"LD Brown","year":"2001","unstructured":"Brown, L. D., Cai, T. T. & DasGupta, A. Interval estimation for a binomial proportion. Stat. Sci. 16, 101\u2013133 (2001).","journal-title":"Stat. Sci."},{"key":"3329_CR28","first-page":"15682","volume":"34","author":"M Minderer","year":"2021","unstructured":"Minderer, M. et al. Revisiting the calibration of modern neural networks. Adv. Neural Inf. Process. Syst. 34, 15682\u201315694 (2021).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3329_CR29","first-page":"15288","volume":"33","author":"J Mukhoti","year":"2020","unstructured":"Mukhoti, J. et al. Calibrating deep neural networks using focal loss. Adv. Neural Inf. Process. Syst. 33, 15288\u201315299 (2020).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3329_CR30","unstructured":"Bishop, C. M. Pattern Recognition and Machine Learning (Springer, 2006)."},{"key":"3329_CR31","doi-asserted-by":"crossref","unstructured":"Vaseli, H., et al. ProtoASNet: Dynamic Prototypes for Inherently Interpretable and Uncertainty-Aware Aortic Stenosis Classification in Echocardiography. In International Conference on Medical Image Computing and Computer-Assisted Intervention, 368\u2013378 (2023).","DOI":"10.1007\/978-3-031-43987-2_36"},{"key":"3329_CR32","doi-asserted-by":"crossref","unstructured":"Selvaraju, R. R., et al. Grad-cam: visual explanations from deep networks via gradient-based localization. Proceedings of the IEEE International Conference on Computer Vision, 618\u2013626 (2017).","DOI":"10.1109\/ICCV.2017.74"},{"key":"3329_CR33","doi-asserted-by":"publisher","first-page":"1129","DOI":"10.1016\/S0895-4356(03)00177-X","volume":"56","author":"AS Glas","year":"2003","unstructured":"Glas, A. S., Lijmer, J. G., Prins, M. H., Bonsel, G. J. & Bossuyt, P. M. The diagnostic odds ratio: a single indicator of test performance. J. Clin. Epidemiol. 56, 1129\u20131135 (2003).","journal-title":"J. Clin. Epidemiol."},{"key":"3329_CR34","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1016\/0002-9343(84)90437-6","volume":"77","author":"MA Hlatky","year":"1984","unstructured":"Hlatky, M. A. et al. Factors affecting sensitivity and specificity of exercise electrocardiography: multivariable analysis. Am. J. Med. 77, 64\u201371 (1984).","journal-title":"Am. J. Med."},{"key":"3329_CR35","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1097\/00001648-199701000-00002","volume":"8","author":"KG Moons","year":"1997","unstructured":"Moons, K. G., van Es, G. A., Deckers, J. W., Habbema, D. J. & Grobbee, D. E. Limitations of sensitivity, specificity, likelihood ratio, and Bayes\u2019 theorem in assessing diagnostic probabilities: a clinical example. Epidemiology 8, 12\u201317 (1997).","journal-title":"Epidemiology"},{"key":"3329_CR36","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1186\/s13244-022-01345-x","volume":"14","author":"AH Koch","year":"2023","unstructured":"Koch, A. H. et al. Analysis of computer-aided diagnostics in the preoperative diagnosis of ovarian cancer: a systematic review. Insights Imaging 14, 34 (2023).","journal-title":"Insights Imaging"},{"key":"3329_CR37","doi-asserted-by":"publisher","first-page":"e630","DOI":"10.1016\/S2589-7500(22)00130-3","volume":"4","author":"B Van Calster","year":"2022","unstructured":"Van Calster, B., Timmerman, S., Geysels, A., Verbakel, J. Y. & Froyman, W. A deep-learning-enabled diagnosis of ovarian cancer. Lancet Digit. Health 4, e630 (2022).","journal-title":"Lancet Digit. Health"},{"key":"3329_CR38","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.ejca.2016.01.007","volume":"58","author":"E Meys","year":"2016","unstructured":"Meys, E. et al. Subjective assessment versus ultrasound models to diagnose ovarian cancer: A systematic review and meta-analysis. Eur. J. Cancer 58, 17\u201329 (2016).","journal-title":"Eur. J. Cancer"},{"key":"3329_CR39","doi-asserted-by":"publisher","first-page":"982","DOI":"10.1016\/j.jclinepi.2005.02.022","volume":"58","author":"JB Reitsma","year":"2005","unstructured":"Reitsma, J. B. et al. Bivariate analysis of sensitivity and specificity produces informative summary measures in diagnostic reviews. J. Clin. Epidemiol. 58, 982\u2013990 (2005).","journal-title":"J. Clin. Epidemiol."},{"key":"3329_CR40","doi-asserted-by":"publisher","first-page":"1706","DOI":"10.1093\/jnci\/djm199","volume":"99","author":"B Van Calster","year":"2007","unstructured":"Van Calster, B. et al. Discrimination between benign and malignant adnexal masses by specialist ultrasound examination versus serum CA-125. J. Natl Cancer Inst. 99, 1706\u20131714 (2007).","journal-title":"J. Natl Cancer Inst."},{"key":"3329_CR41","doi-asserted-by":"crossref","unstructured":"Deng, J., et al. ImageNet: a large-scale hierarchical image database. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 248\u2013255 (2009).","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"3329_CR42","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Goyal, P., Girshick, R., He, K. & Doll\u00e1r, P. Focal loss for dense object detection. Proceedings of the IEEE International Conference on Computer Vision, 2980\u20132988 (2017).","DOI":"10.1109\/ICCV.2017.324"},{"key":"3329_CR43","doi-asserted-by":"crossref","unstructured":"Cubuk, E. D., Zoph, B., Shlens, J. & Le, Q. V. Randaugment: practical automated data augmentation with a reduced search space. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 3008\u20132017 (2020).","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"3329_CR44","first-page":"5998","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A. et al. Attention is all you need. Adv. Neural Inf. Process. Syst. 30, 5998\u20136008 (2017).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3329_CR45","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","volume":"620","author":"K Singhal","year":"2023","unstructured":"Singhal, K. et al. Large language models encode clinical knowledge. Nature 620, 172\u2013180 (2023).","journal-title":"Nature"},{"key":"3329_CR46","doi-asserted-by":"crossref","unstructured":"Gheflati, B. & Rivaz, H. Vision transformers for classification of breast ultrasound images. 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 480\u2013483 (2022).","DOI":"10.1109\/EMBC48229.2022.9871809"},{"key":"3329_CR47","unstructured":"Loshchilov, I. & Hutter, F. Decoupled weight decay regularization. International Conference on Learning Representations (2019)."},{"key":"3329_CR48","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1038\/nature21056","volume":"542","author":"A Esteva","year":"2017","unstructured":"Esteva, A. et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature 542, 115\u2013118 (2017).","journal-title":"Nature"},{"key":"3329_CR49","doi-asserted-by":"crossref","unstructured":"Rey, D. & Neuh\u00e4user, M. Wilcoxon-signed-rank test. In: Lovric M. (ed) International Encyclopedia of Statistical Science (Springer, 2011).","DOI":"10.1007\/978-3-642-04898-2_616"},{"key":"3329_CR50","doi-asserted-by":"crossref","unstructured":"Efron, B. & Hastie, T. Computer Age Statistical Inference: Algorithms, Evidence, and Data Science (Cambridge University Press, 2016).","DOI":"10.1017\/CBO9781316576533"}],"container-title":["Nature Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41591-024-03329-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41591-024-03329-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41591-024-03329-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T18:05:34Z","timestamp":1737482734000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41591-024-03329-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":50,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["3329"],"URL":"https:\/\/doi.org\/10.1038\/s41591-024-03329-4","relation":{},"ISSN":["1078-8956","1546-170X"],"issn-type":[{"value":"1078-8956","type":"print"},{"value":"1546-170X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]},"assertion":[{"value":"11 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 October 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 January 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"E.E., K.S., F.C., E.K. and P.H. have applied for a patent (European patent application 23220765.4) that is pending to a company named Intelligyn. The patent covers methods for a computer-aided diagnostic system to improve generalization and protect against bias. E.E., K.S. and F.C. hold stock in Intelligyn, where E.E. also has an unpaid leadership role. N.C.P.\u2019s institution has received payments for activities not related to this article, including lectures, presentations, expert testimonies, and service on speakers\u2019 bureaus, as well as for travel support. N.C.P. has been an advisory board member of Mindray and GE Healthcare and has held unpaid leadership roles in the POGS Organization of Government Institutions (and the Rizal Medical Service Delivery Network, which are Philippine governmental institutions with the aim to facilitate smooth referral of patients. The other authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}