A Set-based Hybrid Approach (SHA) for MRI Segmentation

This paper describes a new hybrid approach set-based hybrid approach (SHA) for magnetic resonance (MR) image segmentation by integrating two existing techniques, region-grow and threshold level set. To evaluate the proposed approach in performing real world image segmentation task, instead of using well-taken MR-images, we use real-life images collected in a hospital. Comparison of the performance between the two individual techniques and the new hybrid technique demonstrates the effectiveness of the latter