Weighted DenseNet-121 for Osteoporosis Disease Detection using X-ray Images

Weighted DenseNet-121 for Osteoporosis Disease Detection using X-ray Images
  IJETT-book-cover           
  
© 2022 by IJETT Journal
Volume-70 Issue-3
Year of Publication : 2022
Authors : Pallavi Hallappanavar Basavaraja, Shanmugarathinam Ganesarathinam
https://doi.org/10.14445/22315381/IJETT-V70I3P230

How to Cite?

Pallavi Hallappanavar Basavaraja, Shanmugarathinam Ganesarathinam, "Weighted DenseNet-121 for Osteoporosis Disease Detection using X-ray Images," International Journal of Engineering Trends and Technology, vol. 70, no. 3, pp. 266-274, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I3P230

Abstract
Osteoporosis is a bone-related disease that results in loss of bone minerals and medical-related complications. The diagnosis of Osteoporosis disease is a lengthy task and needs various procedures. The identification of this disease is a challenging task in remote areas because of due to the limited higher technological equipment. Medical radiography is still in practice to analyze and diagnose the health of bone for osteoporosis detection. However, due to the noise in X-ray images and there was a larger difference between the patient’s bone shape when it is under lower contrast conditions. The existing models performed osteoporosis detection which was challenging to obtain a satisfactory outcome. They do not interact very strongly with lighter elements, so proposed DenseNet 121 based Convolutional Neural Network (CNN) classification method for osteoporosis disease detection. DenseNet diminishes the problem of vanishing gradient as it needs a few parameters for training the model. The proposed model will consider the feature propagation and takes care of the information that will build the DenseNet-121 architecture. The osteoporosis X-ray images are collected in the proposed DenseNet-121 based CNN method and have the advantage of segmenting vertebral body as well as vertebral foramen detection in the transverse slices, which improves the disease detection accuracy rate. The experimental result shows that the proposed classification using Weighted DenseNet-121 based CNN achieved an accuracy of 87.10%. Whereas, the existing U-net method showed an accuracy of 81.2% for osteoporosis disease detection.

Keywords
Convolutional Neural Network, Medical, Osteoporosis, Vertebral body, X-ray image.

Reference
[1] D. Hussain, and S. M. Han, Computer-Aided Osteoporosis Detection from DXA Imaging, Comput Methods Programs Biomed. 173 (2019) 87-107.
[2] M. R. K. Mookiah, A. Rohrmeier, M. Dieckmeyer, K. Mei, F. K. Kopp, P. B. Noel, J. S. Kirschke, T. Baum, and K. Subburaj, Feasibility of Opportunistic Osteoporosis Screening in Routine Contrast-Enhanced Multidetector Computed Tomography (MDCT) Using Texture Analysis, Osteoporosis International. 29(4) (2018) 825-835.
[3] J. Ghapanchi, M. Zahed, A. Haghnegahdar, N. Niakan, and A. Sadeghzadeh, Osteoporosis and Jaw Abnormalities in Panoramic Radiography of Chronic Liver Failure Patients, Biomed Research International. (2018).
[4] R. F. A. Marar, D. M. Uliyan, and H. A. Al-Sewadi, Mandible Bone Osteoporosis Detection Using Cone-Beam Computed Tomography, Engineering, Technology & Applied Science Research. 10(4) (2020) 6027-6033.
[5] N. Yamamoto, S. Sukegawa, A. Kitamura, R. Goto, T. Noda, K. Nakano, K. Takabatake, H. Kawai, H. Nagatsuka, K. Kawasaki, and Y. Furuki, Deep Learning for Osteoporosis Classification Using Hip Radiographs and Patient Clinical Covariates, Biomolecules. 10(11) (2020) 1534.
[6] Y. Pan, D. Shi, H. Wang, T. Chen, D. Cui, X. Cheng, and Y. Lu, Automatic Opportunistic Osteoporosis Screening Using Low-Dose Chest Computed Tomography Scans Obtained for Lung Cancer Screening, European Radiology. (2020) 1-10.
[7] N. Shankar, S. S. Babu, and C. Viswanathan, Bone Trabecular Analysis of Proximal Femur Radiographs for the Detection of Osteoporosis Using Anisotropic Morlet Wavelet Transform, Cluster Computing. 22(6) (2019) 14513-14523.
[8] I. Aliaga, V. Vera, M. Vera, E. García, M. Pedrera, and G. Pajares, Automatic Computation of Mandibular Indices in Dental Panoramic Radiographs for Early Osteoporosis Detection, Artificial Intelligence in Medicine. 103 (2020) 101816.
[9] P. Keerthika, P. Suresh, R. M. Devi, C. Gunavathi, T. Senapathi, R. P. Kumar, and V. Nikhil, An Intelligent Bio-Inspired System for Detection and Prediction of Osteoporosis, Materials Today: Proceedings. (2020).
[10] S. Ramkumar, and R. Malathi, Detection of Osteoporosis and Osteopenia Using Bone Densitometer–A Simulation Study, Materials Today: Proceedings. 5(1) (2018) 1024-1036.
[11] F. B. Hamzah, F. M. Hamzah, S. F. M. Razali, and J. Zainudin, Bidirectional Recurrence Neural Network Imputation for Recovering Missing Daily Streamflow Data, International Journal of Engineering Trends and Technology. 69 (2021) 8.
[12] S. Pandey, N. K. Nagwani, and S. Verma, Analysis and Design of High Performance Deep Learning Algorithm: Convolutional Neural Networks, International Journal of Engineering Trends and Technology. 69(6) (2021) 216-224.
[13] C. Tang, W. Zhang, H. Li, L. Li, Z. Li, A. Cai, L. Wang, D. Shi, and B. Yan, CNN-Based Qualitative Detection of Bone Mineral Density Via Diagnostic CT Slices for Osteoporosis Screening, Osteoporosis International. (2020) 1-9.
[14] J. Liu, J. Wang, W. Ruan, C. Lin, and D. Chen, Diagnostic and Gradation Model of Osteoporosis Based on Improved Deep U-Net Network, Journal of Medical Systems. 44(1) (2020) 15.
[15] Y. Fang, W. Li, X. Chen, K. Chen, H. Kang, P. Yu, R. Zhang, J. Liao, G. Hong, and S. Li, Opportunistic Osteoporosis Screening in Multi-Detector CT Images Using Deep Convolutional Neural Networks, European Radiology. (2020) 1-12.
[16] R. Su, T. Liu, C. Sun, Q. Jin, R. Jennane, and L. Wei, Fusing Convolutional Neural Network Features with Hand-Crafted Features for Osteoporosis Diagnoses, Neurocomputing. 385 (2020) 300-309.
[17] S. M. Nazia, R. Fathima, Tamilselvi, M. Parisa Beham, and D. Sabarinathan, Diagnosis of Osteoporosis Using Modified U-Net Architecture with Attention Unit in DEXA and X-Ray Images, Journal of X-Ray Science and Technology. (2020) 1-21.
[18] P. Wang, W. She, Z. Mao, X. Zhou, Y. Li, J. Niu, M. Jiang, and G. Huang, Use of Routine Computed Tomography Scans for Detecting Osteoporosis in Thoracolumbar Vertebral Bodies, Skeletal Radiology. 50(2) (2021) 371-379.
[19] Y. Fang, W. Li, X. Chen, K. Chen, H. Kang, P. R. Yu, Zhang, J. Liao, G. Hong, and S. Li, Opportunistic Osteoporosis Screening in Multi-Detector CT Images Using Deep Convolutional Neural Networks, European Radiology. 31(4) (2021) 1831-1842. [Online]. Available: www.github.com/Pallavi-HB/Osteoporotic-analysis