Classification of Lumbar Spine Degenerative Disorders Using Deep Learning Techniques: A CNN-Based Approach
Vaishnavi V K
B.Sc AI ML RCAS2022BAM022
Rathinam College Of Arts And Science Coimbatore, Tamil Nadu,India vaishnavivettivel@gmail.com
Vishnu G
B.Sc AI ML
Rathinam College of Arts and Science Coimbatore, Tamil Nadu,India darsanaajith13@gmail.com
Rcas2022BAM036
Sandhra S
B.Sc AI ML Rcas2022BAM049
Rathinam College of Arts and Science Coimbatore, Tamil Nadu,India sandhra0411@gmail.com
Ms Maneesha P A
Assistant Professor.MCA
Rathinam College of Arts and Science Coimbatore, Tamil Nadu,India vishnuvishnu62510@gmail.com
Darsana A
B.Sc AI ML Rcas2022BAM050
Rathinam College of Arts and Science Coimbatore, Tamil Nadu,India maneeshatlal1996@gmail.com
Abstract—Lumbar spine degeneration is a leading cause of disability worldwide, with conditions such as degenerative disc disease and spinal stenosis posing significant diagnostic and therapeutic challenges. The project explores an AI-based solution to classify these conditions using medical imaging modalities like MRI and CT. Convolutional Neural Networks (CNNs) are employed for their exceptional ability to extract hierarchical image features and automate classification . This work aims to develop a scalable, accurate, and efficient system for diagnosing lumbar spine degeneration. The study involves an extensive literature review, detailed problem analysis, and a comprehensive implementation of CNNs for feature extraction and classification. Results reveal significant improvements in diagnostic accuracy and consistency compared to traditional methods. Future impli- cations include real-time clinical deployment and enhancement of patient outcomes. Lumbar spine degenerative classification is an important project in medical imaging, radiology, and orthopedic research. It typically involves developing models or frameworks for identifying and classifying degenerative conditions of the lumbar spine, such as herniated discs, spinal stenosis, spondylosis, or degenerative disc disease, from imaging modalities like MRI, CT scans, or X-rays.
