The deformity known as scoliosis is defined by a rotation and lateral curvature of the vertebrae. There are three types of adult scoliosis: secondary adult curves, idiopathic adolescent curves, and primary degenerative curves. This study shows how effective deep learning algorithms are in classifying scoliotic and normal spines from spinal X-ray images. In scoliosis patients, the Spine lateral curvature will exceed 10° and be accompanied by vertebral rotation. While it can manifest at any age, it predominantly emerges during adolescence, underscoring the criticality of early detection and intervention. Out of the four deep learning models Visual Geometry Group 16(VGG16), Convolutional Neural Network(CNN), Deep CNN and Two Stage Cascaded CNN. VGG16 model outperformed other models with the highest accuracy, precision, recall, and F1 score, and demonstrated a notable area under the ROC curve(AUC) score of 0.9720. These findings offer a promising advancement in orthopaedic diagnostics, providing a powerful tool for timely and precise interventions for individuals with spinal conditions.