An Optimized Clustering Approach using Tree Seed Algorithm for the Brain MRI Images Segmentation

Clustering algorithms are widely used to segment medical images. However, these techniques difficult perform, especially in brain magnetic resonance images (MRI), given the complexity of anatomical structure tissue, in-homogeneity pixel intensity images, and partial volume noise effects. This will cause algorithm fall into local minima problem; for this reason, it is recommended improve such clustering using optimization obtain better results. In study, we have proposed a developed optimized tree seed (TSA) MRI image. Algorithms tested on real image datasets. The experimental results simulated datasets show that our method has satisfactory regarding Davies-Bouldin index (DBI) compared fuzzy c-mean (FCM) algorithm.