An image analysis method that uses automatic algorithms for the evaluation of herniation classification and geometry in the diagnosis of a herniated inter-vertebral disc (HIVD). Based on a transverse section, the method utilizes a B-spline curve to approximate a circle-like disc boundary and excludes the herniation from other normal parts of the disc boundary. The method therefor attains to feature recognition that classifies the herniation, and the herniation reconstruction that infers the 3D geometry from one or more transverse section. With enhanced resolution provided by the method, a higher diagnostic rate of HIVD is achieved.