Early detection of aortic aneurysm risk from 4-D MR image data

A computer-aided diagnosis method is reported that allows to objectively identify subjects with connective tissue disorders from sixteen-phase 4D (3D+time) aortic MR images. Our automated segmentation method combines level-set and optimal surface segmentation algorithms so that the final aortic surfaces in all 16 cardiac phases are determined in a single optimization process. The resulting aortic lumen surface is registered with an aortic model followed by calculation of modal indices of aortic shape and motion. The modal indices reflect the differences of any individual aortic shape and motion from an average aortic behavior. Support Vector Machine (SVM) classifier is used for classification of normal and connective disease disorder subjects. 4D MR image data sets acquired from 30 normal and connective tissue disorder subjects were used to evaluate the performance of our method. The automated 4D segmentation result produced accurate aortic surfaces in all 16 cardiac phases, covering the aorta from the left- ventricular outflow tract to the diaphragm, yielding sub- voxel accuracy. The computer aided diagnosis method distinguished between normal and connective tissue disorder subjects with a classification correctness of 96.7%.