Lumbar Spine Degenerative Classification

Abstract

Lumbar Spine Degenerative Classification is a deep learning-based initiative focused on the automated analysis of MRI images to detect and categorize spinal disc degeneration. The system classifies images into three levels: normal, mild/moderate, and severe, helping reduce subjectivity in medical diagnosis. By applying an efficient convolutional neural network architecture, the model captures subtle features in spinal structures, leading to improved diagnostic accuracy. This project aims to support healthcare professionals by offering consistent, fast, and reliable assessments of lumbar spine health. It enhances clinical workflows, encourages early detection, and facilitates ongoing monitoring. With a focus on scalability and accessibility, the system can be integrated into medical settings to improve patient care outcomes. The project demonstrates the potential of artificial intelligence in transforming medical imaging and contributes to building a more intelligent and supportive healthcare environment.

Introduction

The Lumbar Spine Degenerative Classification system is an innovative AI-driven tool designed to enhance the diagnosis and grading of lumbar intervertebral disc degeneration using MRI scans. Leveraging deep learning techniques, particularly Convolutional Neural Networks (CNNs) and EfficientDET, the system automates the classification of spinal conditions into categories such as normal, mild, and severe degeneration.jstage.jst.go.jp+1pubmed.ncbi.nlm.nih.gov+1

Key Features

• Advanced Image Processing: The system processes MRI images through preprocessing steps to improve quality and consistency, followed by analysis using CNNs to identify subtle patterns indicative of degeneration.

• User-Friendly Interface: Designed with accessibility in mind, the platform provides clear visual outputs, including heatmaps and bounding boxes, to assist healthcare professionals in clinical decision-making.

• Educational Tool: Beyond diagnostics, the system serves as an educational resource, aiding medical students and professionals in understanding and identifying lumbar spine conditions.

System Architecture

1. Input Layer: MRI images are collected and prepared for analysis.

2. Processing Layer: Utilizes CNNs and EfficientDET for feature extraction and degeneration severity assessment.

3. Output Layer: Delivers classified results with visual annotations to support clinical decisions.

Implementation and Performance

The system employs a structured approach, including data acquisition, annotation, model training, evaluation, and classification. Utilizing datasets such as the RSNA LumbarDISC dataset, the model has demonstrated high accuracy in classifying lumbar spine degeneration. For instance, a CNN model achieved an accuracy of 82% on validation data using axial T2-weighted MRI images

Conclusion

The Lumbar Spine Degenerative Classification system represents a major step forward in the use of artificial intelligence in medical diagnostics. By leveraging a Convolutional Neural Network (CNN), this system efficiently analyses lumbar spine MRI images to detect and classify different stages of disc degeneration. It is designed to support radiologists and healthcare professionals by providing fast, accurate, and consistent results, ultimately improving diagnostic confidence and patient outcomes.The Classification Module plays a central role by automatically identifying and labelling degenerative conditions across various disc levels. This not only reduces manual workload but also helps in tracking the progression of spine-related issues over time. With its ability to generate interpretable outputs and maintain historical records, the system offers a smart, reliable tool that integrates smoothly into clinical workflowenhancing both decision-making and patient care.

References

[1] B. M. Abuhayi, Y. A. Bezabh, and A. M. Ayalew, “Lumbar disease classification using an Involutional neural based VGG Nets (INVGG),” IEEE Access, 2024. [2] Weicong Zhang, Ziyang Chen, Zhihai Su, Zhengyan Wang, “Deep learning-based detection and classification of lumbar disc herniation on magnetic resonance images.” [3] Anshuman Padhi, \"Degenspine Classifier: Degenerative spine classification.” [4] WangthawatLiwrungrueang, “Automatic Detection, Classification, and Grading of Lumbar Intervertebral Disc Degeneration Using an Artificial Neural Network Model.” [5] Kaisi (Kathy) Chen, Lei Zheng, Honghao Zhao, Zihang Wang, “Deep Learning-Based Intelligent Diagnosis of Lumbar Diseases with Multi-Angle View of Intervertebral Disc.” [6] Dr. Viral H. Borisagar, KaushikkumarKeshavlal Rana, Dr. SheshangDegadwala, Dhairya Vyas, “Advanced Classification of Lumbar Spine Degenerative Disorders Using Spine-CNN Attenuation Model.” [7] Ali Al-kubaisi, Nasser N. Khamiss, “A Transfer Learning Approach for Lumbar Spine Disc State Classification.” [8] Paul Klemm, Kai Lawonn, Henry Volzke, “Visualization and Analysis of Lumbar Spine Canal Variability in Cohort Study Data.” [9] Glenn C. Gaviola MD, Raymond Y. Huang MD, PhD, Christine J. Kim MD, Thomas C., “Standardized Classification of Lumbar Spine Degeneration on Magnetic Resonance Imaging Reduces Intra- and Intersubspecialty Variability.” [10] Mina G. Safain, Richard Ogbuji, Jackson Hayes, Steven W. Hwang, “A novel classification system of lumbar disc degeneration.” [11] Ruchi, Dalwinder Singh, Jimmy Singh, Mohammad Khalid Iman Rahmani, \"Lumbar Spine Disease Detection: Enhanced CNN Model With Improved Classification Accuracy\", IEEE Access, 2024. [12] Nityanand Miskin MD 1, Glenn C. Gaviola MD,Raymond Y. Huang\"Standardized Classification of Lumbar Spine Degeneration on Magnetic Resonance Imaging Reduces Intra- and Inter-subspecialty Variability\"- science direct. [13] Z. Soydan, E. Bayramoglu, D. U. Urut, A. C. Iplikcioglu, and C. Sen, “Tracing the disc: The novel qualitative morphometric MRI based disc degeneration classification system,” JOR spine, vol. 7, no. 1, p. e1321, 2024. [14] W. Zhang et al., “Deep learning?based detection and classification of lumbar disc herniation on magnetic resonance images,” JOR spine, vol. 6, no. 3, p. e1276, 2024 [15] D. Abi-Hanna, J. Kerferd, K. Phan, P. Rao, and R. Mobbs, ‘‘Lumbar disk arthroplasty for degenerative disk disease: Literature review,’’ World Neurosurg., vol. 109, pp. 188–196, Jan. 2023

Copyright

Copyright © 2025 Asst. Prof. Bhagya K, Kamran Mukaram, Manojkumar Sajjan, Meti Vinayakumara, Ullas DM. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.