Analytical Design and Applications of Double-Directional IIR Filters

Minimal user interaction in coronary artery centerline extraction is important for computer aided system in Coronary Artery Disease detection. However, manual seeding leads to error propagation most of the time. In this paper, we propose a neighbourhood search feedback mechanism in centerline tracking to overcome this problem. Two contributions from this paper are: (1) Seed Point Optimization where the defined seed point is optimized before tracking is initialized and (2) Backward-Forward Correlation Verification to verify the points before propagate in the tracking process. We evaluate the proposed method using publicly available dataset and demonstrate the results quantitatively and qualitatively. The experimental results demonstrate the reduction in error propagation by our proposed method compare with the method without feedback mechanism.