Classification of Shoulder X-ray Images with Deep Learning Ensemble Models
Source abstract
Abstract
Fractures occur in the shoulder area, which has a wider range of motion than other joints in the body, for various reasons. To diagnose these fractures, data gathered from X-radiation (X-ray), magnetic resonance imaging (MRI), or computed tomography (CT) are used. This study aims to help physicians by classifying shoulder images taken from X-ray devices as fracture/non-fracture with artificial intelligence. For this purpose, the performances of 26 deep learning-based pre-trained models in the detection of shoulder fractures were evaluated on the musculoskeletal radiographs (MURA) dataset, and two ensemble learning models (EL1 and EL2) were developed. The pre-trained models used are ResNet, ResNeXt, DenseNet, VGG, Inception, MobileNet, and their spinal fully connected (Spinal FC) versions. In the EL1 and EL2 models developed using pre-trained models with the best performance, test accuracy was 0.8455, 0.8472, Cohen’s kappa was 0.6907, 0.6942 and the area that was related with fracture class under the receiver operating characteristic (ROC) curve (AUC) was 0.8862, 0.8695. As a result of 28 different classifications in total, the highest test accuracy and Cohen’s kappa values were obtained in the EL2 model, and the highest AUC value was obtained in the EL1 model.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Medical Imaging and Analysis · Artificial Intelligence in Healthcare and Education · COVID-19 diagnosis using AI
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Electrical and Electronics Engineering, Faculty of Engineering, Gazi University, TR 06570 Ankara, Turkey
Department of Orthopaedics and Traumatology, Faculty of Medicine, Gazi University, TR 06570 Ankara, Turkey
Department of Radiology, Faculty of Medicine, Gazi University, TR 06570 Ankara, Turkey
References (37)
Show source-provided references
1. (2020, September 01). Shoulder Fracture 2014. Available online: https://www.assh.org/handcare/condition/shoulder-fracture.
2. Rajpurkar, P., Irvin, J., Bagul, A., Ding, D., Duan, T., Mehta, H., Yang, B., Zhu, K., Laird, D., and Ball, R.L. (2018, January 4–6). MURA Dataset: Towards Radiologist-Level Abnormality Detection in Musculoskeletal Radiographs. Proceedings of the 1st Conference on Medical Imaging with Deep Learning, Amsterdam, The Netherlands.
3. Arm fracture detection in X-rays based on improved deep convolutional neural network10.1016/j.compeleceng.2019.106530 ↗
4. Galal, A., Hisham, F., Mohamed, M., Hassan, S., Ghanim, T., and Nabil, A. (2019, January 9–12). Automatic Recognition of Elbow Musculoskeletal Disorders using Cloud Application. Proceedings of the 2019 8th International Conference on Software and Information Engineering, Cairo, Egypt.10.1145/3328833.3328870 ↗
5. Liang, S., and Gu, Y. (2020). Towards Robust and Accurate Detection of Abnormalities in Musculoskeletal Radiographs with a Multi-Network Model. Sensors, 20.10.3390/s20113153 ↗
6. Abnormality Detection in Musculoskeletal Radiographs Using Capsule Network10.1109/ACCESS.2019.2923008 ↗
7. Cheng, K., Iriondo, C., Calivá, F., Krogue, J., Majumdar, S., and Pedoia, V. (2019, January 13–17). Adversarial Policy Gradient for Deep Learning Image Augmentation. Proceedings of the 22nd International Conference on Medical Image Computing and Computer Assisted Intervention, Shenzhen, China.10.1007/978-3-030-32226-7_50 ↗
8. Pelka, O., Nensa, F., and Friedrich, C.M. (2019, January 27–28). Branding-Fusion of Meta Data and Musculoskeletal Radiographs for Multi-modal Diagnostic Recognition. Proceedings of the IEEE/CVF International Conference on Computer Vision Workshop, Seoul, Korea.10.1109/ICCVW.2019.00059 ↗
9. Automated abnormality detection in lower extremity radiographs using deep learning10.1038/s42256-019-0126-0 ↗
10. Das, H., Pradhan, C., and Dey, N. (2020). Musculoskeletal radiographs classification using deep learning. Deep Learning for Data Analytics: Foundations, Biomedical Applications and Challenges, Academic Press. [1st ed.].
11. Iterative fusion convolutional neural networks for classification of optical coherence tomography images10.1016/j.jvcir.2019.01.022 ↗
12. Mondol, T.C., Iqbal, H., and Hashem, M. (2019, January 26–28). Deep CNN-Based Ensemble CADx Model for Musculoskeletal Abnormality Detection from Radiographs. Proceedings of the 2019 5th International Conference on Advances in Electrical Engineering, Dhaka, Bangladesh.10.1109/ICAEE48663.2019.8975455 ↗
13. Pradhan, N., Dhaka, V.S., and Chaudhary, H. (2019, January 8–9). Classification of Human Bones Using Deep Convolutional Neural Network. Proceedings of the IOP Conference Series: Materials Science and Engineering, International Conference on Startup Ventures: Technology Developments and Future Strategies, Rajasthan, India.10.1088/1757-899X/594/1/012024 ↗
14. Shao, Y., and Wang, X. (2020, January 19–23). A Two Stage Method for Abnormality Diagnosis of Musculoskeletal Radiographs. Proceedings of the International Conference on Pattern Recognition and Artificial Intelligence, Zhongshan, China.10.1007/978-3-030-59830-3_53 ↗
15. Automated detection and classification of the proximal humerus fracture by using deep learning algorithm10.1080/17453674.2018.1453714 ↗
16. Convolutional neural network based diagnosis of bone pathologies of proximal humerus10.1016/j.neucom.2018.11.115 ↗
17. Classifying shoulder implants in X-ray images using deep learning10.1016/j.csbj.2020.04.005 ↗
18. Sezer, A., Sigirci, I.O., and Sezer, H.B. (2017, January 15–18). Shoulder lesion classification using shape and texture features via composite kernel. Proceedings of the 25th Signal Processing and Communications Applications Conference (SIU), Antalya, Turkey.10.1109/SIU.2017.7960658 ↗
19. Capsule network-based classification of rotator cuffpathologies from MRI10.1016/j.compeleceng.2019.106480 ↗
20. Cardiac Arrhythmia Disease Classification Using LSTM Deep Learning Approach
21. Storey, O., Wei, B., Zhang, L., and Mtope, F.R.F. (2020, January 18–21). Adaptive bone abnormality detection in medical imagery using deep neural networks. Proceedings of the 14th International FLINS Conference, Cologne, Germany.10.1142/9789811223334_0110 ↗
22. Yin, S., Peng, Q., Li, H., Zhang, Z., You, X., Liu, H., Fischer, K., Furth, S.L., Tasian, G.E., and Fan, Y. (2019, January 17). Multi-instance Deep Learning with Graph Convolutional Neural Networks for Diagnosis of Kidney Diseases Using Ultrasound Imaging. Proceedings of the International Workshop on Uncertainty for Safe Utilization of Machine Learning in Medical Imaging, Lima, Peru.10.1007/978-3-030-32689-0_15 ↗
23. Dias, D.D.A. (2019). Musculoskeletal Abnormality Detection on X-ray Using Transfer Learning. [Master’s Thesis, Pompeu Fabra University].
24. Khan, M.A., and Kim, J. (2020). Toward Developing Efficient Conv-AE-Based Intrusion Detection System Using Heterogeneous Dataset. Electronics, 9.10.3390/electronics9111771 ↗
25. YAP and TAZ Promote Periosteal Osteoblast Precursor Expansion and Differentiation for Fracture Repair10.1002/jbmr.4166 ↗
26. Bone Fractured Detection Using Machine Learning and Digital Geometry10.1007/978-981-15-7130-5_28 ↗
27. ImageNet Large Scale Visual Recognition Challenge10.1007/s11263-015-0816-y ↗
28. 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 (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
29. Xie, S., Girshick, R., Dollár, P., Tu, Z., and He, K. (2017, January 21–26). Aggregated Residual Transformations for Deep Neural Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.634 ↗
30. 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 (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.243 ↗
31. Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv.
32. 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 (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.308 ↗
33. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L. (2018, January 18–22). MobileNetV2: Inverted Residuals and Linear Bottlenecks. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00474 ↗
34. Kabir, H.M.D., Abdar, M., Jalali, S.M.J., Khosravi, A., Atiya, A.F., Nahavandi, S., and Srinivasan, D. (2020). SpinalNet: Deep neural networkwith gradual input. arXiv.
35. A Threshold Selection Method from Gray-Level Histograms10.1109/TSMC.1979.4310076 ↗
36. Pizer, S.M., Johnston, R.E., Ericksen, J.P., Yankaskas, B.C., and Muller, K.E. (1990, January 22–25). Contrast-limited adaptive histogram equalization: Speed and effectiveness. Proceedings of the First Conference on Visualization in Biomedical Computing, Atlanta, GA, USA.
37. Heckbert, P.S. (1994). Contrast limited adaptive histogram equalization. Graphics Gems IV, Academic Press Professional.