{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T20:56:51Z","timestamp":1790974611686,"version":"4.1.0"},"reference-count":34,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2022,4,4]],"date-time":"2022-04-04T00:00:00Z","timestamp":1649030400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology","doi-asserted-by":"publisher","award":["MOST-110-2221-E-153 -003"],"award-info":[{"award-number":["MOST-110-2221-E-153 -003"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology","doi-asserted-by":"publisher","award":["MOST-110-2634-F-006 -012"],"award-info":[{"award-number":["MOST-110-2634-F-006 -012"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology","doi-asserted-by":"publisher","award":["MOST-110-2218-E-006 -028"],"award-info":[{"award-number":["MOST-110-2218-E-006 -028"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Scaphoid fractures frequently appear in injury radiograph, but approximately 20% are occult. While there are few studies in the fracture detection of X-ray scaphoid images, their effectiveness is insignificant in detecting the scaphoid fractures. Traditional image processing technology had been applied to segment interesting areas of X-ray images, but it always suffered from the requirements of manual intervention and a large amount of computational time. To date, the models of convolutional neural networks have been widely applied to medical image recognition; thus, this study proposed a two-stage convolutional neural network to detect scaphoid fractures. In the first stage, the scaphoid bone is separated from the X-ray image using the Faster R-CNN network. The second stage uses the ResNet model as the backbone for feature extraction, and uses the feature pyramid network and the convolutional block attention module to develop the detection and classification models for scaphoid fractures. Various metrics such as recall, precision, sensitivity, specificity, accuracy, and the area under the receiver operating characteristic curve (AUC) are used to evaluate our proposed method\u2019s performance. The scaphoid bone detection achieved an accuracy of 99.70%. The results of scaphoid fracture detection with the rotational bounding box revealed a recall of 0.789, precision of 0.894, accuracy of 0.853, sensitivity of 0.789, specificity of 0.90, and AUC of 0.920. The resulting scaphoid fracture classification had the following performances: recall of 0.735, precision of 0.898, accuracy of 0.829, sensitivity of 0.735, specificity of 0.920, and AUC of 0.917. According to the experimental results, we found that the proposed method can provide effective references for measuring scaphoid fractures. It has a high potential to consider the solution of detection of scaphoid fractures. In the future, the integration of images of the anterior\u2013posterior and lateral views of each participant to develop more powerful convolutional neural networks for fracture detection by X-ray radiograph is probably important to research.<\/jats:p>","DOI":"10.3390\/diagnostics12040895","type":"journal-article","created":{"date-parts":[[2022,4,4]],"date-time":"2022-04-04T05:50:43Z","timestamp":1649051443000},"page":"895","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":36,"title":["Scaphoid Fracture Detection by Using Convolutional Neural Network"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5068-2570","authenticated-orcid":false,"given":"Tai-Hua","family":"Yang","sequence":"first","affiliation":[{"name":"Department of Biomedical Engineering, National Cheng Kung University, Tainan 701, Taiwan"},{"name":"Department of Orthopedic Surgery, College of Medicine, National Cheng Kung University Hospital, National Cheng Kung University, Tainan 704, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6333-2457","authenticated-orcid":false,"given":"Ming-Huwi","family":"Horng","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Engineering, National Pingtung University, Pingtung 912, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rong-Shiang","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan 701, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yung-Nien","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan 701, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,4,4]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"104776","DOI":"10.1016\/j.compbiomed.2021.104776","article-title":"CSR-Net: Cross-Scale Residual Network for multi-objective scaphoid fracture segmentation","volume":"137","author":"Chen","year":"2021","journal-title":"Comput. Biol. Med."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"459","DOI":"10.1055\/s-0042-104660","article-title":"Imaging of scaphoid fractures according to the new S3 guidelines","volume":"Volume 188","author":"Schmitt","year":"2016","journal-title":"R\u00f6Fo-Fortschritte auf dem Gebiet der R\u00f6ntgenstrahlen und der bildgebenden Verfahren"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1117","DOI":"10.2214\/AJR.19.21478","article-title":"Incorporating cone-beam CT into the diagnostic algorithm for suspected radiocarpal fractures: A new standard of care?","volume":"213","author":"Gibney","year":"2019","journal-title":"AJR Am. J. Roentgenol."},{"key":"ref_4","first-page":"100033","article-title":"Artificial intelligence for diagnosis of fractures on plain radiographs: A scoping review of current literature","volume":"5","author":"Rainey","year":"2021","journal-title":"Intell.-Based Med."},{"key":"ref_5","first-page":"529","article-title":"Bio-medical analysis of breast cancer risk detection based on deep neural network","volume":"12","author":"Mathappan","year":"2020","journal-title":"Int. J. Med. Eng. Inform."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1038\/s42256-020-0148-7","article-title":"Deep learning robotic guideline for autonomous vascular access","volume":"2","author":"Chen","year":"2020","journal-title":"Nat. Mach. Intell."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2653","DOI":"10.1097\/CORR.0000000000001318","article-title":"Is deep learning on par with human observers for detection of radiographically visible and occult fractures of the scaphoid?","volume":"478","author":"Langerhuizen","year":"2020","journal-title":"Clin. Orthop. Relat. Res."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"e216096","DOI":"10.1001\/jamanetworkopen.2021.6096","article-title":"Development and validation of a deep learning model using convolutional neural networks to identify scaphoid fractures in radiographs","volume":"4","author":"Yoon","year":"2021","journal-title":"JAMA Netw. Open"},{"key":"ref_9","unstructured":"Zhaowei, C., and Nuno, V. (2017). Cascade R-CNN: Delving into high quality object detection. arXiv."},{"key":"ref_10","unstructured":"Mingxing, T., and Quoc, V.L. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. arXiv."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"e200260","DOI":"10.1148\/ryai.2021200260","article-title":"Development and validation of a convolutional neural network for automated detection of scaphoid fractures on conventional radiographs","volume":"3","author":"Hendrix","year":"2021","journal-title":"Radiol. Artif. Intell."},{"key":"ref_12","unstructured":"Omeiza, D., Speakman, S., Cintas, C., and Weldermariam, K. (2019). Smooth grad-CAM++: An enhanced inference level visualization technique for deep convolutional neural network models. arXiv."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Tung, Y.C., Su, J.H., Liao, Y.E.W., Chang, C.D., Cheng, Y.F., Chang, W.C., and Chen, B.H. (2011). High-performance scaphoid fracture recognition via effectiveness assessment artificial neural networks. Appl. Sci., 11.","DOI":"10.3390\/app11188485"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Su, J. (2015). Deep residual learning for image recognition. arXiv.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Maaten, L.V.D., Kilian, Q., and Weinberger, K.Q. (2018). Densely connected convolutional networks. arXiv.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, R. (2014). Going deeper with convolutions. arXiv.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref_17","unstructured":"Ren, S., He, K., Girshick, R., and Sun, J. (2015). Faster r-CNN: Towards real-time object detection with region proposal Networks. arXiv."},{"key":"ref_18","unstructured":"Yang, X., Yan, J., Ming, Q., Wang, W., Zhang, X., and Tian, Q. (2021). Rethinking rotated object detection with Gaussian wasserstein distance loss. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Girshick, R. (2015). Fast r-cnn. arXiv.","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"709","DOI":"10.1002\/jemt.23217","article-title":"An effective and accurate identification system of Mycobacterium tuberculosis using convolution neural networks","volume":"82","author":"Kuok","year":"2019","journal-title":"Microsc. Res. Tech."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Dollar, P., He, K., Hariharan, B., and Elomgie, S. (2017, January 21\u201326). Feature pyramid networks for object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Gu, Y., Qin, X., Peng, Y., and Li, L. (2021). Content-augmented feature pyramid network with light linear spatial transformers for object detection. arXiv.","DOI":"10.1049\/ipr2.12575"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., and Kweon, I.S. (2018). CBAM: Convolutional block attention module. arXiv.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1016\/j.neucom.2021.01.021","article-title":"Bi-directional skip connection feature pyramid network and sub-pixel convolution for high-quality object detection","volume":"440","author":"Xiong","year":"2020","journal-title":"Neurocomputing"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Zhong, B., and Ao, K. (2020). Single-stage rotation-decoupled detector for an oriented object. Remote Sens., 12.","DOI":"10.3390\/rs12193262"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"3388","DOI":"10.1109\/TPAMI.2020.2981890","article-title":"Imbalance problems in object detection: A review","volume":"43","author":"Oksuz","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_27","first-page":"213","article-title":"R-peak detection for improved analysis in health informatics","volume":"13","author":"Gupta","year":"2021","journal-title":"Int. J. Med. Eng. Inform."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Gupta, V., Mittal, M., and Mittal, V. (2021). FrWT-PPCA-Based R-peak Detection for Improved Management of Healthcare System. IETE J. Res.","DOI":"10.1080\/03772063.2021.1982412"},{"key":"ref_29","first-page":"1049","article-title":"A Critical Review of Feature Extraction Techniques for ECG Signal Analysis","volume":"102","author":"Gupta","year":"2021","journal-title":"J. Inst. Eng."},{"key":"ref_30","first-page":"27","article-title":"A Critical Review of Various Peak Detection Techniques of ECG Signals","volume":"4","author":"Gautam","year":"2016","journal-title":"i-Manag. J. Digit. Signal Process."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"654","DOI":"10.1161\/CIRCULATIONAHA.105.594929","article-title":"Receiver-operating characteristic analysis for evaluating diagnostic tests and predictive models","volume":"115","author":"Zou","year":"2007","journal-title":"Circulation"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.chemolab.2005.05.004","article-title":"Receiver operating characteristic curves and related decision measures: A tutorial","volume":"80","author":"Brown","year":"2006","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Agustin, T., Utami, E., and Fatta, H.A. (2020, January 24\u201325). Implementation of data augmentation to improve performance CNN method for detecting diabetic retinopathy. Proceedings of the International Conference on Information and Communications Technology (ICOIACT), Yogyakarta, Indonesia.","DOI":"10.1109\/ICOIACT50329.2020.9332019"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Li, H., Singh, B., Nsjibi, M., Wu, Z., and Davis, L.S. (2019). An Analysis of Pre-Training on Object Detection. arXiv.","DOI":"10.1109\/CVPR.2018.00377"}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/12\/4\/895\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T22:49:35Z","timestamp":1760136575000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/12\/4\/895"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,4]]},"references-count":34,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2022,4]]}},"alternative-id":["diagnostics12040895"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics12040895","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,4]]}}}