PSO based multilevel MRI compression using compressive sensing

A multilevel compression method, for magnetic resonance imaging (MRI) images, is presented in this paper. First, the image segmented into frames of equal size. Then, sparsity each frame computed. Based on index value, compressive sensing (CS) compressed/reconstructed at one level four. Particle swarm optimization (PSO) used to optimize amount information be CS reconstruction process, and thresholds, that separate different levels. Two-dimensional sigmoid function suggested as a fitness PSO. Six MRI images are evaluate performance proposed method. The results show considerable gain both peak signal noise ratio (PSNR) (CL), when compared single compression, which commonly considered literature.