SPINE-EDL NET: ENSEMBLE APPROACH FOR CERVICAL SPINAL FRACTURE DETECTION
Main Article Content
Keywords
Ensemble Method, Cervical Spine Fractures, Deep Learning,, Transfer Learning, Binary Classification
Abstract
Deep learning algorithms have shown significant potential for early disease identification and prevention, becoming increasingly popular in recent years. Cervical spine injuries require immediate diagnosis to ensure adequate treatment. Numerous methods have been projected; but, they repeatedly lack accurateness in detecting minor fractures and may surge the false positive rate due to the limitations of single network-based classifiers. Moreover, the shortage of publicly obtainable spine data makes automated cervical spine fracture detection ominously more challenging to attain. To address these issues, we suggest a new and vigorous method called the Spine-Ensemble Deep Learning Network (Spine-EDLNet). Ensemble learning subsidises a vital role in extracting powerful features from image data. Our model harnesses the strengths of three pretrained deep learning networks: EfficientNetV2, InceptionNetV3, and VGG16, united with a majority voting mechanism. Tailored layers are combined into each model to improve fracture classification. Besides, comprehensive data augmentation and preprocessing practices are applied to the dataset before training, successfully overcoming the dataset obtainability challenge. Investigational results validate that Spine-EDLNet outperforms previous models, attaining a maximum accuracy of 99.6%. This methodology purposes to optimize diagnostic accuracy, robustness, and generalization.
References
2. Dunsker, S.B., et al. Deep-learning artificial intelligence model for automated detection of cervical spine fracture on computed tomography (ct) imaging. in Journal of Neurosurgery. 2019. AMER ASSOC NEUROLOGICAL SURGEONS 5550 MEADOWBROOK DRIVE, ROLLING MEADOWS, IL.
3. Bhavya, M.B.S., M.V. Pujitha, and G.L. Supraja. Cervical Spine Fracture Detection Using Pytorch. in 2022 IEEE 2nd International Conference on Mobile Networks and Wireless Communications (ICMNWC). 2022. IEEE.
4. Bland, J.H. and D.R. Boushey. Anatomy and physiology of the cervical spine. in Seminars in arthritis and rheumatism. 1990. Elsevier.
5. Aguirre, M.F.I., A.I. Tsirikos, and A. Clarke, Spinal injuries in the elderly population. Orthopaedics and Trauma, 2020. 34(5): p. 272-277.
6. Dreizin, D., et al., Multidetector CT of blunt cervical spine trauma in adults. Radiographics, 2014. 34(7): p. 1842-1865.
7. Sugandhavesa, N., et al., A multilevel noncontiguous spinal fracture with cervical and thoracic spinal cord injury. International Journal of Surgery Case Reports, 2021. 88: p. 106529.
8. Phonthee, S., et al., Incidence and factors associated with falls in independent ambulatory individuals with spinal cord injury: a 6-month prospective study. Physical therapy, 2013. 93(8): p. 1061-1072.
9. Inaba, K., et al., Cervical spinal clearance: a prospective Western trauma association multi-institutional trial. The journal of trauma and acute care surgery, 2016. 81(6): p. 1122.
10.Copley, P., V. Tilliridou, and A. Jamjoom, Traumatic cervical spine fractures in the adult. British Journal of Hospital Medicine, 2016. 77(9): p. 530-535.
11.Fischer, P.E., et al., Spinal motion restriction in the trauma patient–a joint position statement. Prehospital Emergency Care, 2018. 22(6): p. 659-661.
12.Landais, A., Cervical Spine Fracture Detection by Computer Vision. 2023.
13.Small, J., et al., Ct cervical spine fracture detection using a convolutional neural network. American Journal of Neuroradiology, 2021. 42(7): p. 1341-1347.
14.Adams, M., et al., Computer vs human: deep learning versus perceptual training for the detection of neck of femur fractures. Journal of medical imaging and radiation oncology, 2019. 63(1): p. 27-32.
15.Urakawa, T., et al., Detecting intertrochanteric hip fractures with orthopedist-level accuracy using a deep convolutional neural network. Skeletal radiology, 2019. 48: p. 239-244.
16.Cheng, C.-T., et al., Application of a deep learning algorithm for detection and visualization of hip fractures on plain pelvic radiographs. European radiology, 2019. 29(10): p. 5469-5477.
17.Chung, S.W., et al., Automated detection and classification of the proximal humerus fracture by using deep learning algorithm. Acta orthopaedica, 2018. 89(4): p. 468-473.
18.Gan, K., et al., Artificial intelligence detection of distal radius fractures: a comparison between the convolutional neural network and professional assessments. Acta orthopaedica, 2019. 90(4): p. 394-400.
19.Kim, D. and T. MacKinnon, Artificial intelligence in fracture detection: transfer learning from deep convolutional neural networks. Clinical radiology, 2018. 73(5): p. 439-445.
20.Lindsey, R., et al., Deep neural network improves fracture detection by clinicians. Proceedings of the National Academy of Sciences, 2018. 115(45): p. 11591-11596.
21.Olczak, J., et al., Artificial intelligence for analyzing orthopedic trauma radiographs: deep learning algorithms—are they on par with humans for diagnosing fractures? Acta orthopaedica, 2017. 88(6): p. 581-586.
22.Derkatch, S., et al., Identification of vertebral fractures by convolutional neural networks to predict nonvertebral and hip fractures: a registry-based cohort study of dual X-ray absorptiometry. Radiology, 2019. 293(2): p. 405-411.
23.Pranata, Y.D., et al., Deep learning and SURF for automated classification and detection of calcaneus fractures in CT images. Computer methods and programs in biomedicine, 2019. 171: p. 27-37.
24.Burns, J.E., J. Yao, and R.M. Summers, Vertebral body compression fractures and bone density: automated detection and classification on CT images. Radiology, 2017. 284(3): p. 788-797.
25.Tomita, N., Y.Y. Cheung, and S. Hassanpour, Deep neural networks for automatic detection of osteoporotic vertebral fractures on CT scans. Computers in biology and medicine, 2018. 98: p. 8-15.
26.Muehlematter, U.J., et al., Vertebral body insufficiency fractures: detection of vertebrae at risk on standard CT images using texture analysis and machine learning. European radiology, 2019. 29: p. 2207-2217.
27.Griffith, B., et al., Screening cervical spine CT in a level I trauma center: overutilization? American Journal of Roentgenology, 2011. 197(2): p. 463-467.
28.Athinartrattanapong, N., et al., Prediction score for cervical spine fracture in patients with traumatic neck injury. Neurology research international, 2021. 2021.
29.Gale, S.C., et al., The inefficiency of plain radiography to evaluate the cervical spine after blunt trauma. Journal of Trauma and Acute Care Surgery, 2005. 59(5): p. 1121-1125.
30.Schenarts, P.J., et al., Prospective comparison of admission computed tomographic scan and plain films of the upper cervical spine in trauma patients with altered mental status. Journal of Trauma and Acute Care Surgery, 2001. 51(4): p. 663-669.
31.Salehinejad, H., et al. Deep sequential learning for cervical spine fracture detection on computed tomography imaging. in 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI). 2021. IEEE.
32.Adam Flanders, C.C., Errol Colak, Felipe Kitamura, Hui Ming Lin, Jeff Rudie, John Mongan, Katherine Andriole, Luciano Prevedello, Michelle Riopel, Robyn Ball, Sohier Dane RSNA 2022 Cervical Spine Fracture Detection. 2022.
33.He, K., et al. Deep residual learning for image recognition. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.
34.Salehinejad, H., et al., Recent advances in recurrent neural networks. arXiv preprint arXiv:1801.01078, 2017.
35.Kim, D., et al. Cervical Spine Fracture Detection Through Two-Stage Approach of Mask Segmentation and Windowing Based on Convolutional Neural Network. in 2023 International Conference on Platform Technology and Service (PlatCon). 2023. IEEE.
36.Bayangkari Karno, A.S., et al., Classification of cervical spine fractures using 8 variants EfficientNet with transfer learning. International Journal of Electrical & Computer Engineering (2088-8708), 2023. 13(6).
37.Khushi, H.M.T., et al., Improved Multiclass Brain Tumor Detection via Customized Pretrained EfficientNetB7 Model. IEEE Access, 2023.
38.https://www.kaggle.com/datasets/vuppalaadithyasairam/spine-fracture-prediction-from-xrays/data.
39.Belaid, O.N. and M. Loudini, Classification of brain tumor by combination of pre-trained vgg16 cnn. Journal of Information Technology Management, 2020. 12(2): p. 13-25.
40.Sam, S.M., et al., Offline signature verification using deep learning convolutional neural network (CNN) architectures GoogLeNet inception-v1 and inception-v3. Procedia Computer Science, 2019. 161: p. 475-483.
41.Liu, S., et al., Recent progress in the cuhk dysarthric speech recognition system. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2021. 29: p. 2267-2281.
42.Zhang, Q.-L. and Y.-B. Yang. Sa-net: Shuffle attention for deep convolutional neural networks. in ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2021. IEEE.
43.Mahum, R., et al., Tran-DSR: A hybrid model for dysarthric speech recognition using transformer encoder and ensemble learning. Applied Acoustics, 2024. 222: p. 110019.
44.Chłąd, P. and M.R. Ogiela, Deep learning and cloud-based computation for cervical spine fracture detection system. Electronics, 2023. 12(9): p. 2056.
45.Karno, A.B., et al., Classification of cervical spine fractures using 8 variants EfficientNet with transfer learning. International Journal of Electrical and Computer Engineering (IJECE), 2023. 13(6): p. 7065-7077.
46.Naguib, S.M., et al., Classification of cervical spine fracture and dislocation using refined pre-trained deep model and saliency map. Diagnostics, 2023. 13(7): p. 1273.
Article Sidebar
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
All articles published in JPTCP are licensed under Copyright Creative Commons Attribution-NonCommercial 4.0 International License.
Tahira Kanwal
Department of Computer Science, University of Engineering and Technology Taxila, Pakistan
Rabbia Mahum
Department of Computer Science, University of Engineering and Technology Taxila, Pakistan
Syed Aun Irtaza
Department of Computer Science, University of Engineering and Technology Taxila, Pakistan
Usama Irshad
pDepartment of Computer Science, University of Engineering and Technology Taxila, Pakistan
Romail Khan
Department of Computer Science, University of Engineering and Technology Taxila, Pakistan
Faisal Shafique Butt
Department of Computer Science, Comsats University Islamabad, Wah Campus