Volume no :
9 |
Issue no :
02
Article Type :
Scholarly Article
Author :
Sanika Kare , Samiksha Pachpol, Prof. K. S. Telangre
Published Date :
June, 2025
Publisher :
Journal of Artificial Intelligence and Cyber Security (JAICS)
Page No: 1 - 6
Abstract : This study uses a computer program (AI) to automatically find and identify problems in the lower back (lumbar spine) from MRI scans. We trained the AI on a lot of MRI pictures to recognize common issues like slipped discs and narrowed spinal canals. The AI did a good job, correctly identifying problems most of the time. This shows that computers can help doctors look at MRI scans faster and more accurately. We believe this can lead to quicker and better diagnoses for patients with back pain. In the future, we want to make the AI even better and use it in real hospitals The integration of machine learning (ML) and artificial intelligence (AI) in medical imaging has marked a significant advancement in diagnostic precision and efficiency, especially in the evaluation of lumbar spine diseases. This project leverages advanced deep learning techniques to enhance the analysis of lumbar spine MRI scans, which is essential for diagnosing conditions such as Spinal Canal Stenosis, Neural Foraminal Narrowing, and Subarticular Stenosis. The importance of this initiative extends beyond just improving diagnostic accuracy; it also aims to address critical healthcare system challenges like prolonged waiting times and restricted access to specialist care.
Keyword Lumbar Spine Diseases. Deep Learning, Natural Language Processing, MRI Imaging, Multimodal Data, Disease Clarification, Artificial Intelligence, Diagnostic Accuracy, Medical Imaging, Spinal Disorder, Machine Learning, Machine Learning, Image Segmentation, Clinical Decision Support
Reference:
  1. Kirkham, J. R., & Smith, R. J. (2018). Inter-observer variability in the interpretation of lumbar spine MRI: A systematic review. Journal of Radiology, 45(3), 123-130. doi:10.1016/j.jr.2018.01.005
  2. Kumar, A., & Gupta, R. (2019). Machine learning approaches for classification of lumbar spine disorders: A review. Medical Image Analysis, 54, 1-12. doi:10.1016/j.media.2019.01.002
  3. Wang, Y., Zhang, L., & Chen, H. (2020). Deep learning for lumbar spine disease classification using MRI: A convolutional neural network approach. Neurocomputing, 392, 1-10. doi:10.1016/j.neucom.2020.01.012
  4. Zhang, T., Li, X., & Zhao, Y. (2021). Multimodal deep learning for lumbar spine disease detection: Integrating MRI and radiology reports. Artificial Intelligence in Medicine, 113, 101- 110. doi:10.1016/j.artmed.2021.101110
  5. Lee, J., Park, S., & Kim, H. (2022). Transfer learning for lumbar spine disease detection: A case study using pre-trained convolutional neural networks. Journal of Biomedical Informatics, 127, 103-115. doi:10.1016/j.jbi.2022.103115
  6. Smith, A. B., & Johnson, C. D. (2023). Evaluating the generalizability of AI models in medical imaging: A systematic review. Journal of Medical Imaging, 10(2), 45-58. doi:10.1117/1.JMI.10.2.024501
  7. Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017). Grad-CAM: Visual explanations from deep networks via gradient-based localization. International Conference on Computer Vision (ICCV), 618-626. doi:10.1109/ICCV.2017.74

8. Esteva, A., Kuprel, B., Novoa, R. A., et al. (2017). Dermatologist-level classification of skin cancer  with deep neural networks. Nature, 542(7639), 115-118. doi:10.1038/nature21056