DSAN6500 Final Project
According to the World Health Organization, lower back (lumbar spine) pain is a leading cause of disability across the world, affecting more than 600 million people (2023). Many people will experience lumbar spine pain at some point in their lives, and it is increasingly prevalent with age. Efficient and accurate diagnosis of lumbar spine conditions is essential for dictating treatment and speeding rehabilitation (Richards et al., 2024). The importance of this project is to use machine learning and artificial intelligence in tandem with computer vision techniques to aid in the detection as well as the classification of five specific lumbar spine degenerative conditions. The five degenerative conditions being studied are: Left neural Foraminal Narrowing, Right Neural Foraminal Narrowing, Left Subarticular Stenosis, Right Subarticular Stenosis, and Spinal Canal Stenosis. Rapid detection of degenerative conditions through machine learning will lead to improved medical treatment, improving patient outcomes and quality of life for millions worldwide. According to current research, there has already been work done in the Deep Learning space where Convolutional Neural Networks have been used for detection and classification of medical conditions. For our specific use case, there has not been research done on the previously mentioned 5 conditions that we hope to detect and classify. Due to the current lack of an automated method, we hope to evaluate multiple Neural Network models that are accurate enough to detect and classify the 5 degenerative conditions.
- Richards, T., Talbott, J., Ball, R., Colak, E., Flanders, A., Kitamura, F., Mongan, J., Prevedello, L., & Vazirabad, M. (2024). RSNA 2024 Lumbar Spine Degenerative Classification. Kaggle. https://kaggle.com/competitions/rsna-2024-lumbar-spine-degenerative-classification