{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,12]],"date-time":"2026-11-12T14:19:20Z","timestamp":1794493160602,"version":"4.9.1"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T00:00:00Z","timestamp":1746662400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T00:00:00Z","timestamp":1746662400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Accurate diagnosis of orthopedic injuries, especially pelvic and hip fractures, is vital in trauma management. While pelvic radiographs (PXRs) are widely used, misdiagnosis is common. This study proposes an automated system that uses convolutional neural networks (CNNs) to detect potential fracture areas and predict fracture conditions, aiming to outperform traditional object detection-based systems. We developed two deep learning models for hip fracture detection and prediction, trained on PXRs from three hospitals. The first model utilized automated hip area detection, cropping, and classification of the resulting patches. The images were preprocessed using the Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm. The YOLOv5 architecture was employed for the object detection model, while three different pre-trained deep neural network (DNN) architectures were used for classification, applying transfer learning. Their performance was evaluated on a test dataset, and compared with 35 clinicians. YOLOv5 achieved a 92.66% accuracy on regular images and 88.89% on CLAHE-enhanced images. The classifier models, MobileNetV2, Xception, and InceptionResNetV2, achieved accuracies between 94.66% and 97.67%. In contrast, the clinicians demonstrated a mean accuracy of 84.53% and longer prediction durations. The DNN models showed significantly better accuracy and speed compared to human evaluators (<jats:italic>p<\/jats:italic>\u2009&lt;\u20090.0005, <jats:italic>p<\/jats:italic>\u2009&lt;\u20090.01). These DNN models highlight promising utility in trauma diagnosis due to their high accuracy and speed. Integrating such systems into clinical practices may enhance the diagnostic efficiency of PXRs. <\/jats:p>","DOI":"10.1038\/s41598-025-98852-w","type":"journal-article","created":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T07:37:53Z","timestamp":1746689873000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["An automated hip fracture detection, classification system on pelvic radiographs and comparison with 35 clinicians"],"prefix":"10.1038","volume":"15","author":[{"given":"Abdurrahim","family":"Yilmaz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kadir","family":"Gem","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mucahit","family":"Kalebasi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rahmetullah","family":"Varol","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zuhtu Oner","family":"Gencoglan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yegor","family":"Samoylenko","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hakan Koray","family":"Tosyali","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guvenir","family":"Okcu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huseyin","family":"Uvet","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,5,8]]},"reference":[{"key":"98852_CR1","first-page":"111","volume":"89","author":"A Pinto","year":"2018","unstructured":"Pinto, A. et al. Traumatic fractures in adults: Missed diagnosis on plain radiographs in the Emergency Department. Acta Bio Medica Atenei Parmensis 89, 111 (2018).","journal-title":"Acta Bio Medica Atenei Parmensis"},{"key":"98852_CR2","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1097\/TA.0000000000001324","volume":"82","author":"CC Burlew","year":"2017","unstructured":"Burlew, C. C. et al. Preperitoneal pelvic packing reduces mortality in patients with life-threatening hemorrhage due to unstable pelvic fractures. J. Trauma Acute Care Surg. 82, 233\u2013242 (2017).","journal-title":"J. Trauma Acute Care Surg."},{"issue":"1","key":"98852_CR3","doi-asserted-by":"publisher","first-page":"11","DOI":"10.5371\/hp.2020.32.1.11","volume":"32","author":"YJ Seong","year":"2020","unstructured":"Seong, Y. J., Shin, W. C., Moon, N. H. & Suh, K. T. Timing of hip-fracture surgery in elderly patients: Literature review and recommendations. Hip Pelvis 32(1), 11 (2020).","journal-title":"Hip Pelvis"},{"key":"98852_CR4","doi-asserted-by":"publisher","first-page":"1064","DOI":"10.1002\/jbmr.4821","volume":"38","author":"CW Sing","year":"2023","unstructured":"Sing, C. W. et al. global epidemiology of hip fractures: Secular trends in incidence rate, post-fracture treatment, and all-cause Mortality. J. Bone Miner. Res. 38, 1064\u20131075 (2023).","journal-title":"J. Bone Miner. Res."},{"key":"98852_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13017-019-0248-z","volume":"14","author":"CH Chou","year":"2019","unstructured":"Chou, C. H. et al. Hemostasis as soon as possible? The role of the time to angioembolization in the management of pelvic fracture. World J. Emerg. Surg. 14, 1\u20138 (2019).","journal-title":"World J. Emerg. Surg."},{"issue":"9156","key":"98852_CR6","doi-asserted-by":"publisher","first-page":"878","DOI":"10.1016\/S0140-6736(98)09075-8","volume":"353","author":"JR Center","year":"1999","unstructured":"Center, J. R., Nguyen, T. V., Schneider, D., Sambrook, P. N. & Eisman, J. A. Mortality after all major types of osteoporotic fracture in men and women: An observational study. The Lancet 353(9156), 878\u2013882 (1999).","journal-title":"The Lancet"},{"issue":"Suppl 12","key":"98852_CR7","first-page":"76","volume":"90","author":"C Artoni","year":"2019","unstructured":"Artoni, C. et al. Pelvic ring fractures: What about timing?. Acta Bio Medica: Atenei Parmensis 90(Suppl 12), 76 (2019).","journal-title":"Acta Bio Medica: Atenei Parmensis"},{"issue":"3","key":"98852_CR8","doi-asserted-by":"publisher","first-page":"881","DOI":"10.1007\/s00530-021-00884-5","volume":"28","author":"R Yousef","year":"2022","unstructured":"Yousef, R., Gupta, G., Yousef, N. & Khari, M. A holistic overview of deep learning approach in medical imaging. Multimed. Syst. 28(3), 881\u2013914 (2022).","journal-title":"Multimed. Syst."},{"issue":"1","key":"98852_CR9","doi-asserted-by":"publisher","first-page":"1066","DOI":"10.1038\/s41467-021-21311-3","volume":"12","author":"CT Cheng","year":"2021","unstructured":"Cheng, C. T. et al. A scalable physician-level deep learning algorithm detects universal trauma on pelvic radiographs. Nat. Commun. 12(1), 1066. https:\/\/doi.org\/10.1038\/s41467-021-21311-3 (2021).","journal-title":"Nat. Commun."},{"issue":"2","key":"98852_CR10","doi-asserted-by":"publisher","first-page":"190023","DOI":"10.1148\/ryai.2020190023","volume":"2","author":"JD Krogue","year":"2020","unstructured":"Krogue, J. D. et al. Automatic hip fracture identification and functional subclassification with deep learning. Radiol. Artif. Intell. 2(2), 190023 (2020).","journal-title":"Radiol. Artif. Intell."},{"key":"98852_CR11","doi-asserted-by":"publisher","first-page":"109139","DOI":"10.1016\/j.ejrad.2020.109139","volume":"130","author":"G Kitamura","year":"2020","unstructured":"Kitamura, G. Deep learning evaluation of pelvic radiographs for position, hardware presence, and fracture detection. Eur. J. Radiol. 130, 109139 (2020).","journal-title":"Eur. J. Radiol."},{"issue":"1","key":"98852_CR12","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1186\/s12891-021-04260-2","volume":"22","author":"Y Sato","year":"2021","unstructured":"Sato, Y. et al. Artificial intelligence improves the accuracy of residents in the diagnosis of hip fractures: A multicenter study. BMC Musculoskelet. Disord. 22(1), 407 (2021).","journal-title":"BMC Musculoskelet. Disord."},{"key":"98852_CR13","doi-asserted-by":"publisher","first-page":"12258","DOI":"10.1038\/s41598-024-63093-w","volume":"14","author":"JM Lee","year":"2024","unstructured":"Lee, J. M. et al. Deep-learning-based pelvic automatic segmentation in pelvic fractures. Sci. Rep. 14, 12258 (2024).","journal-title":"Sci. Rep."},{"key":"98852_CR14","doi-asserted-by":"publisher","first-page":"2658","DOI":"10.3390\/diagnostics13162658","volume":"13","author":"MU Saeed","year":"2023","unstructured":"Saeed, M. U. et al. An automated deep learning approach for spine segmentation and vertebrae recognition using computed tomography images. Diagnostics 13, 2658 (2023).","journal-title":"Diagnostics"},{"key":"98852_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105153","volume":"86","author":"MU Saeed","year":"2023","unstructured":"Saeed, M. U., Bin, W., Sheng, J., Ali, G. & Dastgir, A. 3D MRU-Net: A novel mobile residual U-Net deep learning model for spine segmentation using computed tomography images. Biomed. Signal Process. Control 86, 105153 (2023).","journal-title":"Biomed. Signal Process. Control"},{"key":"98852_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.105943","volume":"91","author":"MU Saeed","year":"2024","unstructured":"Saeed, M. U., Bin, W., Sheng, J., Albarakati, H. M. & Dastgir, A. MSFF: An automated multi-scale feature fusion deep learning model for spine fracture segmentation using MRI. Biomed. Signal Process. Control 91, 105943 (2024).","journal-title":"Biomed. Signal Process. Control"},{"issue":"5","key":"98852_CR17","doi-asserted-by":"publisher","first-page":"2216","DOI":"10.1007\/s10278-024-01091-0","volume":"37","author":"MU Saeed","year":"2024","unstructured":"Saeed, M. U. et al. An automated multi-scale feature fusion network for spine fracture segmentation using computed tomography images. J. Imaging Informat. Med. 37(5), 2216\u20132226 (2024).","journal-title":"J. Imaging Informat. Med."},{"key":"98852_CR18","doi-asserted-by":"publisher","first-page":"105540","DOI":"10.1016\/j.jmbbm.2022.105540","volume":"137","author":"R Caron","year":"2023","unstructured":"Caron, R., Londono, I., Seoud, L. & Villemure, I. Segmentation of trabecular bone microdamage in Xray microCT images using a two-step deep learning method. J. Mech. Behav. Biomed. Mater. 137, 105540 (2023).","journal-title":"J. Mech. Behav. Biomed. Mater."},{"key":"98852_CR19","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1007\/s00256-022-04160-z","volume":"52","author":"S Faghani","year":"2023","unstructured":"Faghani, S. et al. A deep learning algorithm for detecting lytic bone lesions of multiple myeloma on CT. Skeletal. Radiol. 52, 91\u201398 (2023).","journal-title":"Skeletal. Radiol."},{"key":"98852_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2022.e11266","author":"N Twinprai","year":"2017","unstructured":"Twinprai, N. et al. Artificial intelligence (AI) vs. human in hip fracture detection. Heliyon https:\/\/doi.org\/10.1016\/j.heliyon.2022.e11266 (2017).","journal-title":"Heliyon"},{"issue":"7","key":"98852_CR21","doi-asserted-by":"publisher","first-page":"105","DOI":"10.3390\/jimaging7070105","volume":"7","author":"G Reichert","year":"2021","unstructured":"Reichert, G. et al. How can a deep learning algorithm improve fracture detection on X-rays in the emergency room?. J. Imaging 7(7), 105. https:\/\/doi.org\/10.3390\/jimaging7070105 (2021).","journal-title":"J. Imaging"},{"issue":"6","key":"98852_CR22","doi-asserted-by":"publisher","first-page":"522","DOI":"10.3390\/jpm11060522","volume":"11","author":"FY Liu","year":"2021","unstructured":"Liu, F. Y. et al. Automatic hip detection in anteroposterior pelvic radiographs\u2014A labelless practical framework. J. Personal. Med 11(6), 522. https:\/\/doi.org\/10.3390\/jpm11060522 (2021).","journal-title":"J. Personal. Med"},{"key":"98852_CR23","doi-asserted-by":"crossref","unstructured":"Selvaraju, R. R., et al. Grad-cam: Visual explanations from deep networks via gradient-based localization. In Proceedings of the IEEE International Conference on Computer (2017).","DOI":"10.1109\/ICCV.2017.74"},{"key":"98852_CR24","doi-asserted-by":"publisher","first-page":"847","DOI":"10.1007\/s11548-020-02150-x","volume":"15","author":"A Jim\u00e9nez-S\u00e1nchez","year":"2020","unstructured":"Jim\u00e9nez-S\u00e1nchez, A. et al. Precise proximal femur fracture classification for interactive training and surgical planning. Int. J. Comput. Assist. Radiol. Surg. 15, 847\u2013857 (2020).","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"98852_CR25","doi-asserted-by":"publisher","first-page":"030006052110001","DOI":"10.1177\/03000605211000157","volume":"49","author":"L Jiang","year":"2021","unstructured":"Jiang, L. et al. Opportunities and challenges of artificial intelligence in the medical field: Current application, emerging problems, and problem-solving strategies. J. Int. Med. Res. 49, 03000605211000157 (2021).","journal-title":"J. Int. Med. Res."},{"key":"98852_CR26","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0314196","volume":"19","author":"MS Razai","year":"2024","unstructured":"Razai, M. S. et al. Implementation challenges of artificial intelligence (AI) in primary care: Perspectives of general practitioners in London UK. PLoS ONE 19, e0314196 (2024).","journal-title":"PLoS ONE"},{"key":"98852_CR27","volume":"15","author":"MI Ahmed","year":"2023","unstructured":"Ahmed, M. I. et al. A systematic review of the barriers to the implementation of artificial intelligence in healthcare. Cureus 15, e46454 (2023).","journal-title":"Cureus"},{"key":"98852_CR28","doi-asserted-by":"publisher","first-page":"1","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, 1\u20139. https:\/\/doi.org\/10.1186\/s12916-019-1426-2 (2019).","journal-title":"BMC Med."},{"issue":"5","key":"98852_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3234150","volume":"51","author":"S Pouyanfar","year":"2018","unstructured":"Pouyanfar, S. et al. A survey on deep learning: Algorithms, techniques, and applications. ACM Comput. Surv. (CSUR) 51(5), 1\u201336 (2018).","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"98852_CR30","unstructured":"Perez, L.,& J. W. The effectiveness of data augmentation in image classification using deep learning. http:\/\/arxiv.org\/abs\/1712.04621 (2017)."},{"issue":"11","key":"98852_CR31","doi-asserted-by":"publisher","first-page":"3212","DOI":"10.1109\/TNNLS.2018.2876865","volume":"30","author":"ZQ Zhao","year":"2019","unstructured":"Zhao, Z. Q., Zheng, P., Xu, S. T. & Wu, X. Object detection with deep learning: A review. IEEE Trans. Neural Netw. Learn. Syst. 30(11), 3212\u20133232 (2019).","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"98852_CR32","unstructured":"HumanSignal\/labelImg. https:\/\/github.com\/HumanSignal\/labelImg."},{"key":"98852_CR33","doi-asserted-by":"publisher","unstructured":"ultralytics\/yolov5: v7.0\u2014YOLOv5 SOTA Realtime Instance Segmentation. https:\/\/doi.org\/10.5281\/ZENODO.7347926.","DOI":"10.5281\/ZENODO.7347926"},{"key":"98852_CR34","unstructured":"Pizer, S. M., Johnston, R. E., Ericksen, J. P., Yankaskas, B. C. & Muller, K. E. Contrast-limited adaptive histogram equalization: Speed and effectiveness stephen m. pizer, r. eugene johnston, james p. ericksen, bonnie c. yankaskas, keith e. muller medical image display research group. In Proceedings of the First Conference on Visualization in Biomedical Computing (1990)."},{"key":"98852_CR35","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","volume":"42","author":"G Litjens","year":"2017","unstructured":"Litjens, G. et al. A survey on deep learning in medical image analysis. Med. Image Anal. 42, 60\u201388 (2017).","journal-title":"Med. Image Anal."},{"key":"98852_CR36","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 (2016).","DOI":"10.1109\/CVPR.2016.90"},{"key":"98852_CR37","unstructured":"Pan, S., et al. A survey on transfer learning. IEEE Trans. Knowl. Data Eng. (2009)."},{"key":"98852_CR38","unstructured":"Yosinski, J., et al. How transferable are features in deep neural networks? In Advances in Neural Information Processing Systems (2014)."},{"key":"98852_CR39","unstructured":"Krizhevsky, A., et al. Imagenet classification with deep convolutional neural networks. In Proceedings (2012)."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-98852-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-98852-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-98852-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T07:38:03Z","timestamp":1746689883000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-98852-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,8]]},"references-count":39,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["98852"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-98852-w","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,8]]},"assertion":[{"value":"28 June 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 April 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 May 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"16001"}}