CPR For MR Spine Images

Medical image processing is using image visual processing method of auxiliary clinical diagnosis is an important technology, therefore, in recent years gradually becomes the research focus. Curved planar reformation for MR spinal images is of great significance to computer aided information recognition and clinical research of the spine pathology. If the spine is not properly posited and surface reconstructed, the so-called computer description of clinical value will be limited. The traditional positioning for the whole spine takes so long time that it is difficult to be accepted. Therefore the automatic computer assistant diagnosis for locating disc has important value of clinical applications.This paper accurate effectively eliminates scoliosis on location through two methods based on quantitative analysis of MR images. One is reconstruction from original sagittal images to coronal, and another is synthesis of the water images and fat images. On the basis of the spine and fitting the centerline of spine, MC algorithm is used to output triangular mesh model to reconstruct the spine center surface. The efficiency of the proposed algorithm is demonstrated by experiments using real MR images provided by College of Medicine, University of Cincinnati. And we also propose further improvement in this study.