Spinal cord injury (SCI) is a serious medical condition. Spinal Cord Injury limits the movement of the body, blocks the nervous system and affects the quality of life of an injured patient. Spinal cord injury (SCI) detection is one of the major problems. Earlier, to detect spinal cord injury, radiologists analyze SCI images manually but manual interpretation of high dimensional feature space makes it difficult to predict the exact category and level of severity of injury. For better analysis of the spinal cord injury, technology must be used . Recent advances in the medical field of SCI has played a significant role in improving diagnosis, stabilization and well being of injured patient. Technology, like machine learning, deep learning, image segmentation can help to detect spinal cord injury in an improved manner. This paper focuses on study of related work done on detection of Spinal Cord Injury and also proposes a novel model for detection of spinal cord injury.