AUTOMATIC DETECTION AND SEGMENTATION OF THE SPINAL CANAL IN COMPUTED TOMOGRAPHIC IMAGES

摘要

A method for the automatic three-dimensional segmentation of the spinal canal in computed tomographic (CT) images is presented. The method uses a priori radiological and anatomical information, mathematical morphology, and region-growing methods. The skin and peripheral fat structures are determined by delineating the air and other materials external to the body. Using the fat layer as reference, the bone structure is segmented. The Hough transform for the detection of circles is applied to a cropped bone edge map that includes the thoracic vertebral structure. The centers of the detected circles are used as the seed voxels for the fuzzy connectivity algorithm that is employed to segment the spinal canal. The method was successfully applied to eight CT volumes of four patients.