Feature selection algorithm for classification of multispectral MR images using constrained energy minimization

This study proposes a new unsupervised approach for targets detection and classification in multispectral Magnetic Resonance (MR) images. The proposed method comprises two processes, namely Target Generation Process (TGP) and Constrained Energy Minimization (CEM). TGP is a fuzzy-set process that generates a set of potential targets from unknown information, and applies these targets to be desired targets in CEM Finally, the real MR images are used in the experiments to evaluate the effectiveness of proposed method. Experiment results reveal that the proposed method segments a multispectral MR image much more effectively than either FMRIB´s Automated Segmentation Tool (FAST) or Fuzzy C-means (FC).