A NOVEL HYBRID ALGORITHM FOR STITCHING OF SPINE MAGNETIC RESONANCE IMAGES

The technique of merging several overlapping images from the similar viewpoint into a superior one without defeat of information is known as an image stitching. The utilization of scale invariant feature transform (SIFT) and Random Sample Consensus (RANSAC) techniques to stitch the C-T-L (cervical-thoracic-lumbar) spine magnetic resonance (MRI) images to provide the entire view of spine in a solo flawless image is the rationale of this study. All MRI images were obtained by the fast spin echo (FSE) pulse sequence using MRI scanners. Because of the limitations of MRI scanners, whenever Patients go through spinal cord examination, three different images of C-T-L sections of spine are generated. For diagnostic purpose, it is desired to have single flawless image of entire spinal cord. For the improvement of diagnosis of spine the proposed approach can be performed best. We believe that our approach can be supportive for the medical purpose and extension of other medicinal imaging modalities for image stitching. The stitching process for every section of spine MRI image were performed and implemented on a graphic user interface (GUI) configuration.