ABSTRACT
In this paper, we propose an approach based on 2D vessel model to segment the vessel lumen in three-dimensional coronary computed tomographic angiography (CCTA) images. The 2D parametric intensity model is introduced first to simulate the intensity distribution of vessel lumen with different size in the longitudinal images. Then the Levenberg-Marquardt method is applied to fit the model within a series of region-of interests defined in the longitudinal image. The estimated parameters of the model are employed to define the boundary points of vessel lumen. The detected boundary points of vessel lumen in six longitudinal images are transformed to the cross-sectional planes in order to calculate the degree of stenosis according to the luminal areas. Our proposed method was evaluated in ten CCTA images with ten reported non-calcified stenosis. The degree of each stenosis was computed according to the luminal area and compared with the standard reference given by radiologists. Experimental results show that our method can estimate the degree of stenosis with a high accuracy.
