2690-6791ISSN (Online)
2769-786XISSN (Print)
Volume 16 , Issue 2 , PP: 214-235, 2025 | Cite this article as | XML | Html | PDF | Full Length Article
Woud Majid Abed 1 * , Murtadha M. Hamad 2 , Azmi Tawfeq Hussein Alrawi 3
Doi: https://doi.org/10.54216/JISIoT.160216
This study investigates combining fuzzy logic with deep learning methodologies in classifying X-ray images for osteoporosis detection. Osteoporosis, defined by compromised bone integrity and heightened fracture susceptibility, requires prompt and precise diagnosis for effective treatment. We devised a hybrid approach that amalgamates transfer learning from Convolutional Neural Network (CNN) architectures, including MobileNetV2, AlexNet, ResNet50V2, and Xception, utilizing fuzzy logic during the preprocessing phase to address uncertainty and imprecision in X-ray images, thereby enhancing the quality of the input data for the subsequent pre-trained models. The research entailed the examination of a significant dataset of X-ray images and the implementation of the proposed methodology to categorize images as osteoporotic or non-osteoporotic, attaining a remarkable accuracy of 99.68% and a receiver operating characteristic (ROC) of 100% through the integration of fuzzy logic preprocessing with ResNet50V2. This innovative method may substantially decrease diagnostic inaccuracies and enhance patient outcomes, facilitating additional research and development in applying deep learning techniques in healthcare.
Osteoporosis Detection , X-ray Classification , Deep Learning , Transfer Learning, Fuzzy Logic
[1] S. Sharma and A. K. Singh, "Quantum Convolutional Neural Networks for Image Classification," IEEE Transactions on Quantum Engineering, vol. 2, pp. 1–9, 2021, doi: 10.1109/TQE.2021.3062523.
[2] J. Li, R. Zhang, and M. He, "Deep Learning for Medical Image Classification: A Comprehensive Review," IEEE Access, vol. 8, pp. 123841–123856, 2020, doi: 10.1109/ACCESS.2020.3006070.
[3] X. Liu, J. Han, and Y. Wang, "A Novel Deep Learning Model for Brain Tumor Classification Using MRI Images," IEEE Transactions on Medical Imaging, vol. 40, no. 10, pp. 2555–2565, 2021, doi: 10.1109/TMI.2021.3082109.
[4] M. Yousif, B. Al-Khateeb, and B. Garcia-Zapirain, "A New Quantum Circuits of Quantum Convolutional Neural Network for X-RAY Images Classification," IEEE Access, vol. 12, 2024, doi: 10.1109/ACCESS.2024.3396411.
[5] D. Chen, P. Sun, and W. Zhou, "Hybrid Attention Networks for Disease Prediction," Neural Networks, vol. 142, pp. 313–325, 2022, doi: 10.1016/j.neunet.2021.10.014.
[6] M. A. Mohammed et al., "Novel Crow Swarm Optimization Algorithm and Selection Approach for Optimal Deep Learning COVID-19 Diagnostic Model," Computers, Materials & Continua, vol. 73, no. 1, pp. 1–16, 2022, doi: 10.32604/cmc.2022.019761.
[7] X. Niu et al., "Development and validation of a fully automated system using deep learning for opportunistic osteoporosis screening using low-dose computed tomography scans," Quantitative Imaging in Medicine and Surgery, vol. 13, no. 8, pp. 5294–5305, Aug. 2023, doi: 10.21037/qims-22-1438.
[8] G. Namratha Meedinti, K. S. Srirekha, and R. Delhibabu, "A Quantum Convolutional Neural Network Approach for Object Detection and Classification," arXiv preprint arXiv: 2307.08204, 2023.
[9] L. Zhang and K. Wang, "Multimodal Fusion of CT and MRI for Brain Disease Detection," IEEE Transactions on Neural Networks and Learning Systems, vol. 34, no. 4, pp. 1231–1242, 2023, doi: 10.1109/TNNLS.2023.3258729.
[10] H. Wei, J. Xu, and C. Li, "3D Convolutional Neural Networks for Alzheimer’s Disease Classification," Neurocomputing, vol. 458, pp. 377–388, 2021, doi: 10.1016/j.neucom.2021.06.008.
[11] R. Kumar and A. Gupta, "Transfer Learning for Medical Image Classification: A Review," Journal of Biomedical Informatics, vol. 113, p. 103632, 2021, doi: 10.1016/j.jbi.2021.103632.
[12] J. Park, M. Kim, and S. Yoon, "Attention Mechanisms in Medical Image Processing: A Review," Pattern Recognition, vol. 125, p. 108586, 2022, doi: 10.1016/j.patcog.2021.108586.
[13] X. Feng, Q. Wang, and J. Tang, "MRI-Based Parkinson’s Disease Diagnosis Using CNN-LSTM Model," IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 30, pp. 1524–1535, 2022, doi: 10.1109/TNSRE.2022.3187536.
[14] M. Arabahmadi, R. Farahbakhsh, and J. Rezazadeh, "Deep Learning for Smart Healthcare: A Survey on Brain Tumor Detection," Sensors, vol. 22, no. 5, 2022, doi: 10.3390/s22051960.
[15] M. Liu and D. Zhang, "Alzheimer's Disease Classification Based on Individual Hierarchical Networks Constructed With 3D CNNs," Frontiers in Neuroscience, vol. 14, p. 570, 2020, doi: 10.3389/fnins.2020.00570.
[16] K. Shin, D. Park, and Y. Kim, "Explainable AI for Medical Image Classification Using Deep Learning," IEEE Transactions on Medical Imaging, vol. 41, no. 2, pp. 399–412, 2022, doi: 10.1109/TMI.2021.3124209.
[17] A. Patel, P. Sharma, and R. Verma, "Hybrid CNN-RNN Model for Breast Cancer Detection," Medical Image Analysis, vol. 80, p. 102311, 2023, doi: 10.1016/j.media.2022.102311.
[18] Y. Wang, G. Li, and X. Zhou, "Deep Transfer Learning for Retinal Disease Classification," IEEE Journal of Biomedical and Health Informatics, vol. 27, no. 1, pp. 89–100, 2023, doi: 10.1109/JBHI.2022.3214532.
[19] J. Sun and W. Zhang, "Self-Supervised Learning for Medical Image Segmentation," IEEE Transactions on Medical Imaging, vol. 40, no. 6, pp. 1731–1742, 2021, doi: 10.1109/TMI.2021.3062783.
[20] M. Hassan and A. Iqbal, "Comparative Analysis of Deep Learning Models for Skin Lesion Classification," Biomedical Signal Processing and Control, vol. 74, p. 103553, 2022, doi: 10.1016/j.bspc.2022.103553.
[21] T. Nakamura and K. Yoshida, "Few-Shot Learning for Medical Image Classification," Pattern Recognition Letters, vol. 149, pp. 63–70, 2021, doi: 10.1016/j.patrec.2021.05.006.
[22] H. Zhao, J. Liu, and F. Wang, "Deep Learning-Based Early Detection of Lung Cancer Using CT Scans," IEEE Transactions on Biomedical Engineering, vol. 69, no. 2, pp. 215–225, 2022, doi: 10.1109/TBME.2021.3074982.
[23] S. Das and B. Sen, "Hybrid Deep Learning Approaches for Brain Tumor Segmentation," Artificial Intelligence in Medicine, vol. 126, p. 102193, 2022, doi: 10.1016/j.artmed.2022.102193.
[24] A. A. Khan, M. U. Farooq, and R. Ahmed, "AI-Powered COVID-19 Detection Using Chest X-rays," IEEE Access, vol. 9, pp. 123123–123134, 2021, doi: 10.1109/ACCESS.2021.3078495.
[25] Y. Chen, X. Zhao, and R. Wang, "Deep Reinforcement Learning for Medical Diagnosis: A Review," Artificial Intelligence in Medicine, vol. 125, p. 102202, 2022, doi: 10.1016/j.artmed.2022.102202.
[26] A. K. Gupta, R. Singh, and P. Kumar, "Hybrid Deep Learning Model for Early Detection of Diabetes Using IoT-Based Health Monitoring Systems," IEEE Internet of Things Journal, vol. 10, no. 3, pp. 2547–2560, 2023, doi: 10.1109/JIOT.2022.3188943.
[27] S. J. Kim, D. H. Lee, and H. Kwon, "Contrastive Learning for Medical Image Analysis: A Survey," IEEE Transactions on Medical Imaging, vol. 42, no. 5, pp. 1311–1325, 2023, doi: 10.1109/TMI.2023.3236578.
[28] N. Roy, B. Adhikari, and S. Paul, "Improved Medical Image Classification Using Hybrid CNN-LSTM Model," Biomedical Signal Processing and Control, vol. 80, p. 104002, 2023, doi: 10.1016/j.bspc.2023.104002.
[29] D. Lin, J. Zhu, and M. Xu, "Automated Skin Cancer Detection Using Deep Learning on Dermoscopic Images," IEEE Transactions on Biomedical Engineering, vol. 69, no. 11, pp. 3215–3226, 2022, doi: 10.1109/TBME.2022.3145427.
[30] H. Zhang, Y. Sun, and X. Chen, "Deep Learning-Based Optical Coherence Tomography Image Classification for Ophthalmology," IEEE Transactions on Neural Networks and Learning Systems, vol. 34, no. 2, pp. 435–448, 2023, doi: 10.1109/TNNLS.2023.3269045.
[31] W. Pan, K. Li, and S. Yu, "3D Vision-Based AI Techniques for Medical Image Processing: A Review," Pattern Recognition, vol. 132, p. 108946, 2022, doi: 10.1016/j.patcog.2022.108946.
[32] T. Ahmed, P. Shankar, and A. B. Patel, "A Comparative Study on Federated Learning for Privacy-Preserving Medical Image Analysis," IEEE Transactions on Big Data, vol. 9, no. 4, pp. 1327–1340, 2023, doi: 10.1109/TBDATA.2023.3260893.
