Aorta segmentation in non-contrast cardiac CT images using an entropy-based cost function

Studies have shown that aortic calcification is associated with increased risk of cardiovascular disease. Furthermore, aortic calcium assessment can be performed on standard cardiac calcium scoring Computed Tomography scans, which may help to avoid additional imaging studies. In this paper, we present an entropy-based, narrow band restricted, iterative method for segmentation of the ascending aorta in non-contrast CT images, as a step towards aortic calcification detection and pericardial fat quantitation. First, an estimate of the aorta center and radius is obtained by applying dynamic programming in Hough space. In the second step, these estimates serve to reduce the aorta boundary search area to within a narrow band, and the contour is updated iteratively using dynamic programming methods. Our algorithm is able to overcome the limitations of previous approaches in characterizing (i) the boundary edge features and (ii) non-circular shape at aortic root. The results from the proposed method compare favorably with the manually traced aorta boundaries and outperform other approaches in terms of boundary distance and volume overlap.