MR Brain Image Segmentation based on Markov Random Field with the Application of ACO

Magnetic resonance (MR) medical image segmentation plays an increasingly important role in computer-aided detection and diagnosis (CAD) of abnormalities. MRI segmentation manually is time consuming and consumes valuable human resources. Hence a great deal of efforts has been made to automate this process. Markov Random Field (MRF) has been one of the most active research areas of MRI brain segmentation which seeks an optimal label field in a large space. The traditional optimization method is Simulated Annealing (SA) that could get the global optimal solution with heavy computation burden. Therefore great deal efforts have been made to obtain the optimal solution in a reasonable time. In this paper, we conduct a comparative study with the traditional minimization approach Simulated Annealing (SA) and a novel proposed method: MRF-Hybrid Parallel Ant Colony Optimization (MRF-HPACO) with Fuzzy C-Means (FCM) Algorithm for the segmentation of MR images. Comparing with Simulated Annealing (SA) and MRF with Improved Genetic Algorithm (MRF-IGA) that is often used in the image segmentations based on Markov Random Field (MRF) models, HPACO has been used in reducing the computation complexity of optimization. There are M colonies, M-1 colonies treated as slaves and one colony for master. Each colonies visit all the pixels without revisit. Initially, initialize the pheromone value for all the colonies. Posterior energy values are computed by Markov Random Field. If this value is less than global minimum, the local minimum is assigned to global minimum. The pheromone of the Ant that generates the global minimum is updated. At the final iteration global minimum returns the optimum threshold value for select the initial clustering the FCM implementation in the brain Magnetic Resonance Image (MRI) segmentation.The qualitative and quantitative results of each system are investigated as well.