CLASSIFICATION OF VARIOUS STAGES OF HERNIATED CERVICAL SPINE IMAGES USING EDGE DETECTION OPERATORS

A herniated disc is a state that can happen anywhere along the spine, but utmost in the lower back and neck. Cervical discs are the cushionsthat can link the vertebrae in the upper back and neck. When the gelatinous inner disc material, the nucleus pulposus ruptures or herniates through the outer cervical disc wall it can lead to herniation. Some herniated disc causes no symptoms but other disc related problems can irritate nearby nerves and result in pain, numbness or weakness in an arm or leg. In this work, cervical spine abnormal (herniated) Magnetic Resonance Images (MRI) are taken for classification. Generally, there are four stages of herniation in cervicalspine named as disc degeneration, disc prolapse, disc extrusion and disc sequestration. These herniated cervical spine images are transformed into herniated canny images, because canny edge detection algorithm is better to provide high image quality and allows removing of any noise in an image. Artificial Neural Network classifier is used for classifying the different stages of images. It follows the supervised learning method, and is the process of learning to separate samples into different classes by finding common features between samples of known classes. In this paper, various stages of herniated canny images are processed with different level of combinations of texture features are analyzed. Classification is done on different stages of herniated cervical spine images. This classification is used in different variants and utilizes it with suitable algorithm to improve its performance.