Segmentation of coronary arteriograms by iterative ternary classification

A segmentation algorithm for extracting arterial structures in coronary angiograms is presented. The algorithm mimics the process of interactive interpretation in human vision by iteratively implementing a ternary classification and learning process. Two gray-scale thresholds are computed to define three pixel classes: artery, background, and undecided. Then, two new thresholds for undecided pixels are computed using statistics conditioned by the current classification. The threshold adaptation is governed by a learning algorithm based on the line and consistency measurements around each pixel. The process converges and results in a binary image. The performance of this algorithm on human coronary arteriograms was compared qualitatively to that of a relaxation algorithm and of a scattering-based algorithm. Quantitative comparison was also made possible with computer generated images, which were obtained with the help of a model of the imaging chain and a process of interactive visualization of the modeled data. The iterative ternary classifier showed the best performance over a broad range of image quality. The study also demonstrated the use of visualization and user interaction in model building and algorithm development.