Precise segmentation of spinal vertebrae are crucial within the study of spinal connected disorders likes bone fractures. Distinguishing severity of fractures and understanding its causes canl help facilitate physicians confirm the foremost effective pharmacological treatments and clinical management methods for spinal disorders. Though image segmentation has been a wide analysis area, restricted work has been done on investigating and segmenting vertebrae. The complexness of vertebrae shapes, gaps within the cortical bone, internal boundaries, as well as the noisy, incomplete or missing data from the medical images have undoubtedly inflated the challenge. In this work, a technique is presented for fuzzy segmentation of two-dimensional Computed Tomography (CT) images. This method is followed by an advanced shape driven level set segmentation, where the level set evolution is guided by a shape constraint and driven by a shape energy combined with a Gaussian kernel. Experimental results on CT images of spinal vertebrae demonstrate the practicability of our proposed framework. Our final goal is to produce a quantitative platform for economical and correct diagnosis of spinal disorder connected diseases.