High-Performance Scaphoid Fracture Recognition via Effectiveness Assessment of Artificial Neural Networks
Source abstract
Abstract
Image recognition through the use of deep learning (DL) techniques has recently become a hot topic in many fields. Especially for bioimage informatics, DL-based image recognition has been successfully used in several applications, such as cancer and fracture detection. However, few previous studies have focused on detecting scaphoid fractures, and the related effectiveness is also not significant. Aimed at this issue, in this paper, we present a two-stage method for scaphoid fracture recognition by conducting an effectiveness analysis of numerous state-of-the-art artificial neural networks. In the first stage, the scaphoid bone is extracted from the radiograph using object detection techniques. Based on the object extracted, several convolutional neural networks (CNNs), with or without transfer learning, are utilized to recognize the segmented object. Finally, the analytical details on a real data set are given, in terms of various evaluation metrics, including sensitivity, specificity, precision, F1-score, area under the receiver operating curve (AUC), kappa, and accuracy. The experimental results reveal that the CNNs with transfer learning are more effective than those without transfer learning. Moreover, DenseNet201 and ResNet101 are found to be more promising than the other methods, on average. According to the experimental results, DenseNet201 and ResNet101 can be recommended as considerable solutions for scaphoid fracture detection within a bioimage diagnostic system.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Orthopedic Surgery and Rehabilitation · Forensic Anthropology and Bioarchaeology Studies · Medical Malpractice and Liability Issues
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Diagnostic Radiology, Kaohsiung Chang Gung Memorial Hospital, Chang Gung University College of Medicine, Kaohsiung 83347, Taiwan
Department of Computer Science and Information Engineering, National University of Kaohsiung, Kaohsiung 83347, Taiwan
Department of Information Management, Cheng Shiu University, Kaohsiung 83347, Taiwan
Funding
Ministry of Science and Technology
References (44)
Show source-provided references
1. Application of GMDH neural network technique to improve measuring precision of a simplified photon attenuation based two-phase flowmeter10.1016/j.flowmeasinst.2020.101804 ↗
2. Arab, F., Karimi, M., and Safavi, S.M. (2016, January 20–21). Analysis of QoS parameters for video traffic in homeplug AV standard using NS-3. Proceedings of the 2016 Smart Grids Conference, Kerman, Iran.10.1109/SGC.2016.7882949 ↗
3. Black-box identification and validation of an induction motor in an experimental application10.18280/ejee.210219 ↗
4. Tavakoli, S., and Yooseph, S. (2019, January 18–21). Algorithms for inferring multiple microbial networks. Proceedings of the 2019 IEEE International Conference on Bioinformatics and Biomedicine, San Diego, CA, USA.10.1109/BIBM47256.2019.8983194 ↗
5. Nisar, M.U., Voghoei, S., and Ramaswamy, L. (2017, January 5–8). Caching for pattern matching queries in time evolving graphs: Challenges and approaches. Proceedings of the 2017 IEEE 37th International Conference on Distributed Computing System, Atlanta, GA, USA.10.1109/ICDCS.2017.57 ↗
6. Design and tri-objective optimization of an energy plant integrated with near-zero energy building including energy storage: An application of dynamic simulation
7. Protein contact map prediction based on ResNet and DenseNet
8. A survey on image data augmentation for deep learning10.1186/s40537-019-0197-0 ↗
9. Application of machine learning in ophthalmic imaging modalities10.1186/s40662-020-00183-6 ↗
10. Convolutional neural network based on dynamic motion and shape variations for elderly fall detection10.18178/ijmlc.2019.9.6.878 ↗
11. Automated segmentation of tissues using CT and MRI: A systematic review10.1016/j.acra.2019.07.006 ↗
12. Deep-learning-based image reconstruction and enhancement in optical microscopy
13. Ghoneim, S. (2021, July 23). Accuracy, Recall, Precision, F-Score & Specificity, Which to Optimize on? Based on Your Project, Which Performance Metric to Improve on? Towards Data Science. Available online: https://towardsdatascience.com/accuracy-recall-precision-f-score-specificity-which-to-optimize-on-867d3f11124.
14. Automated abnormality classification of chest radiographs using deep convolutional neural networks10.1038/s41746-020-0273-z ↗
15. Liver semantic segmentation algorithm based on improved deep adversarial networks in combination of weighted loss function on abdominal CT images10.1109/ACCESS.2019.2929270 ↗
16. Francis, N.S., Francis, N.J., Xu, Y., Saqib, M., and Aljasar, S.A. (2020, January 17–19). Identify Cancer in Affected Bronchopulmonary Lung Segments Using Gated-SCNN Modelled with RPN. Proceedings of the 2020 IEEE 6th International Conference on Control Science and Systems Engineering, Beijing, China.10.1109/ICCSSE50399.2020.9171947 ↗
17. Javan, N.A., Jebreili, A., Mozafari, B., and Hosseinioun, M. (2021). Classification and Segmentation of Pulmonary Lesions in CT images using a combined VGG-XGBoost method, and an integrated Fuzzy Clustering-Level Set technique. arXiv.
18. He, X., Chen, K., Hu, K., Chen, Z., Li, X., and Gao, X. (2020, January 16–19). HMOE-Net: Hybrid Multi-scale Object Equalization Network for Intracerebral Hemorrhage Segmentation in CT Images. Proceedings of the 2020 IEEE International Conference on Bioinformatics and Biomedicine, Seoul, Korea.10.1109/BIBM49941.2020.9313439 ↗
19. Deep learning for hemorrhagic lesion detection and segmentation on brain ct images10.1109/JBHI.2020.3028243 ↗
20. Wang, Z., Wu, L., and Ji, X. (2021, January 22–24). An Interpretable Deep Learning System for Automatic Intracranial Hemorrhage Diagnosis with CT Image. Proceedings of the 2021 International Conference on Bioinformatics and Intelligent Computing, Harbin, China.10.1145/3448748.3448803 ↗
21. A multiorgan segmentation model for CT volumes via full convolution-deconvolution network10.1155/2017/6941306 ↗
22. Infrared Handprint Classification Using Deep Convolution Neural Network10.1007/s11063-021-10429-6 ↗
23. Classification of Musculoskeletal Abnormalities with Convolutional Neural Networks
24. MSFCN-multiple supervised fully convolutional networks for the osteosarcoma segmentation of CT images10.1016/j.cmpb.2017.02.013 ↗
25. Binomial classification of pediatric elbow fractures using a deep learning multiview approach emulating radiologist decision making10.1148/ryai.2019180015 ↗
26. Detection of traumatic pediatric elbow joint effusion using a deep convolutional neural network10.2214/AJR.18.19974 ↗
27. Artificial intelligence for analyzing orthopedic trauma radiographs: Deep learning algorithms—are they on par with humans for diagnosing fractures?10.1080/17453674.2017.1344459 ↗
28. Artificial intelligence in fracture detection: Transfer learning from deep convolutional neural networks10.1016/j.crad.2017.11.015 ↗
29. Special x-ray projections in assessment of scaphoid bone fractures
30. Cone-beam CT in diagnosis of scaphoid fractures10.1007/s00256-015-2290-6 ↗
31. Ozkaya, E., Topal, F.E., Bulut, T., Gursoy, M., Ozuysal, M., and Karakaya, Z. (2020). Evaluation of an artificial intelligence system for diagnosing scaphoid fracture on direct radiography. Eur. J. Trauma Emerg. Surg.10.1007/s00068-020-01468-0 ↗
32. Bochkovskiy, A., Wang, C.Y., and Liao, H.Y.M. (2020). Yolov4: Optimal speed and accuracy of object detection. arXiv.
33. Redmon, J., and Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv.
34. Wang, C.Y., Liao, H.Y.M., Wu, Y.H., Chen, P.Y., Hsieh, J.W., and Yeh, I.H. (2020, January 14–19). CSPNet: A new backbone that can enhance learning capability of CNN. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Seattle, WA, USA.10.1109/CVPRW50498.2020.00203 ↗
35. Spatial pyramid pooling in deep convolutional networks for visual recognition10.1109/TPAMI.2015.2389824 ↗
36. Liu, S., Qi, L., Qin, H., Shi, J., and Jia, J. (2018, January 18–23). Path aggregation network for instance segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00913 ↗
37. Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv.
38. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
39. Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21–26). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.243 ↗
40. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016, January 27–30). Rethinking the inception architecture for computer vision. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.308 ↗
41. Tan, M., and Le, Q. (2019, January 9–15). Efficientnet: Rethinking model scaling for convolutional neural networks. Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA.
42. Effective Semantic Annotation by Image-to-Concept Distribution Model10.1109/TMM.2011.2129502 ↗
43. Efficient Relevance Feedback for Content-Based Image Retrieval by Mining User Navigation Patterns10.1109/TKDE.2010.124 ↗
44. (2021, September 09). RSNA Pediatric Bone Age Challenge (2017). Available online: https://www.rsna.org/education/ai-resources-and-training/ai-image-challenge/rsna-pediatric-bone-age-challenge-2017.