International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Ensemble Deep Learning Framework for Osteoporosis Detection Using Lumbar Spine DXA Images |
|---|---|
| ABSTRACT | Osteoporosis is a progressive skeletal disorder characterized by reduced bone mineral density, leading to an increased risk of vertebral fractures. Early detection is crucial; however, conventional diagnosis using Dual-Energy X-ray Absorptiometry (DXA) is often constrained by expert dependency and limited accessibility. This paper proposes an automated ensemble deep learning framework for osteoporosis detection using lumbar spine DXA images. The proposed approach integrates a custom Convolutional Neural Network (CNN), a fine-tuned VGG16 model, and a ResNet-based feature extractor combined with a Random Forest classifier through a stacking ensemble strategy. Experimental results demonstrate that the ensemble model outperforms individual classifiers, achieving an accuracy of 97.03% and a ROC–AUC score of 0.99, indicating high diagnostic reliability. The proposed framework shows strong potential as an effective clinical decision-support system for early osteoporosis screening, particularly in resource-limited healthcare settings. |
| AUTHOR | PROF. SHWETHA G, AVINASH K, DEVIKA T A, GANESH M V, SANKETHA K A Assistant Professor, Department of Computer Science and Design, Bapuji Institute of Engineering and Technology, Davanagere, Karnataka, India B.E Student, Department of Computer Science and Design, Bapuji Institute of Engineering and Technology, Davanagere, Karnataka, India |
| VOLUME | 177 |
| DOI | 10.15680/IJIRCCE.2025.1312069 |
| pdf/69_Ensemble Deep Learning Framework for Osteoporosis Detection Using Lumbar Spine DXA Images.pdf | |
| KEYWORDS | |
| References | [1] J. A. Kanis, A. Borgstrom, C. De Laet, et al., “Assessment of osteoporosis at the primary health-care level,” World Health Organization Scientific Group, WHO Technical Report, 2008. [2] International Osteoporosis Foundation, “Osteoporosis facts and statistics,” Available: https://www.osteoporosis.foundation/facts-statistics, Accessed: 2023. G. M. Blake and I. Fogelman, “The role of XA bone density scans in the diagnosis and treatment of osteoporosis,” Postgraduate Medical Journal, vol. 83, no. 982, pp. 509–517, 2007. [3] G. Litjens, T. Kooi, B. E. Bejnordi, et al., “A survey on deep learning in medical image analysis,” Medical Image Analysis, vol. 42, pp. 60–88, 2017. [4] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition,” roceedings of the IEEE, vol. 86, no. 11, pp. 2278–2324, 1998. [5] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, pp. 436–444, 2015. [6] K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv preprint arXiv:1409.1556, 2014. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770–778. [7] L. Breiman, “Random forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001. [8] C. Shorten and T. M. Khoshgoftaar, “A survey on image data augmentation for deep learning,” Journal of Big Data, vol. 6, no. 1, pp. 1–48, 2019. [9] T. Fawcett, “An introduction to ROC analysis,” Pattern Recognition Letters, vol. 27, no. 8, pp. 861–874, 2006. [10] D. M. W. Powers, “Evaluation: From precision, recall and F-measure to ROC, informedness and correlation,” Journal of Machine Learning Technologies, vol. 2, no. 1, pp. 37–63, 2020. [11] P. Rajpurkar, E. J. Topol, et al., “Artificial intelligence in medical imaging: Current challenges and future directions,” Radiology, vol. 304, no. 3, pp. 500–512, 2022. [12] A.A.Khan and M. H. Nasir, “Ensemble convolutional neural networks for improved medical image classification,” in Proc. IEEE Int. Conf. Machine Learning and Applications (ICMLA), 2021. [13] L.Xue, Y.Wang, et al.,“FCoTNet: An attention-based CNN for osteoporosis detection on lumbar spine X-ray images,” IEEE Access, vol. 11, pp. 44832–44844, 2023. [14] N. Hong, J. Lee, and Y. Yoon, “Deep learning-based vertebral fracture and osteoporosis detection using spine radiographs,” European Radiology, vol. 33, no. 4, pp. 2472–2481, 2023. [15] S. L. Yeh, M. Huang, et al., “Automated bone mineral density assessment using deep neural networks on DXA images,” IEEE Access, vol. 10, pp. 11245–11256, 2022. [16] V. R. Murthy and P. Kumar, “Explainable artificial intelligence in osteoporosis diagnosis: A survey,” Biomedical Signal Processing and Control, vol. 82, 2023. [17] W. N. Price, “Medical artificial intelligence and the law,” Journal of Law and Biosciences, vol. 6, no. 1, pp. 1–36, 2019. [18] E. J. Topol, “High-performance medicine: The convergence of human and artificial intelligence,” Nature Medicine, vol. 25, pp. 44–56, 2019. [19] J. Tang, H. Liu, et al., “Multimodal fusion of clinical data and X-ray images for osteoporosis diagnosis,” Computers in Biology and Medicine, 2025. |
