University of Houston

Studies have shown that aortic calcification is associated with an increased risk of cardiovascular disease. In this work, a method for localization, centerline extraction and segmentation of the thoracic aorta in non-contrast cardiac computed tomography images, towards aortic calcification detection, is presented. A novel method to determine the location of a slice of interest (in this case, the right coronary artery ostium slice) within the volume is presented, by formulating it as a regression problem. The input variables for the regression are obtained from simple intensity features computed from a pyramid representation of the slice. The localization, centerline extraction, and segmentation of the aorta are formulated as optimal path detection problems. Dynamic programming is applied in the Hough space for localization of key centerpoints in the aorta which guide the centerline tracing using a fast marching-based minimal path extraction framework. The input volume is then resampled into a stack of 2D cross-sectional planes orthogonal to the obtained centerline. Dynamic programming is again applied for the segmentation of the aorta in the each slice of the resampled volume. A narrow band restricted, iterative segmentation method is proposed, that utilizes local entropy to characterize boundary features and allows deviation from non-circular shape to capture the varying shape of the aorta near its root. The obtained segmentation is finally mapped back to its original volume space. The performance of the proposed method was assessed on a dataset of 47 volumes and promising results were obtained.