Image Segmentation is an important part of image processing which can be used to separate objects in images, ignoring the effects of lights and textures. The higher resolution and better spatial discrimination of soft tissues make MRI an effective method among other medical diagnostic modalities. The existing Particle Swarm Optimization (PSO) technique is not much effective approach since the space for feasible solutions of min – cut partitioning problem is excessively large, particularly when the number of vertices is in the thousands. In this paper, multilevel segregating method is combined with discrete PSO and developed Multilevel Iterative Discrete Particle Swarm Optimization algorithm (MIDPSO) for min – cut partitioning. MIDPSO works in three steps- partitioning phase, refinement phase, and recursive partition. The classifier Support Vector Machine (SVM), based on structured risk minimization is used here. By selecting the best features in the dataset; SVM increases the performance as well as reduces the computational time complexity. The proposed technique considers local as well as global to meet the requirement of precise segmentation. The proposed method aims in classifying the healthy and pathological tissues in the MRI images with high sensitivity, specificity and accuracy in least time.