Study of Supervised Segmentation Algorithm Based on Ant Colony for Putamen Region in Brain MRI
A supervised segmentation algorithm based on ant colony for putamen region in brain MRI is proposed. Since the variance of the putamen template and the searching contour is adopted as the object function, the solution process for the supervised ant colony algorithm model proposed is transformed as the process of the minimum of the object function, or as the optimal searching path problem in the search space. A new scheme for finding search space is proposed, and discusses how to decide the optimal searching scheme. By a general hypothesis for the template, the solution process for the problem is described in detail. A great deal of experimental results show that the supervised segmentation algorithm based on ant colony proposed is better than the Fuzzy c-Mean segmentation, region growth segmentation, GVF(Gradient Vector Flow) Snake model segmentation and the basic ant colony segmentation in the shape of the real template, the shape comparability between adjoining slices and the continuity in single slice. Moreover, the convergence speed of the proposed algorithm is the fastest than the others.