Here we provide a novel method in the compression of MRI image. For the compression we use contextual vector quantization (CVQ) and Listless set partitioning in hierarchical trees (LSPIHT). In pre-processing we remove the noise from the image. In this method, a contextual region is defined as a region containing the most important information and must be encoded without considerable quality loss. Attempts are made to encode this region with high priority and high resolution (low compression ratio and high bit rate) CVQ algorithm. Here Background region will be compressed by Contextual vector quantization. Then the CROI will be compressed by Listless set partitioning in hierarchical trees (LSPIHT). The background, which has a lower priority, is separately encoded with a low resolution (high compression ratio and low bit rate). The ROI is set on higher priority, since it has more important information for diagnostic purposes. The information of the ROI image should not be loss. Finally both of the encoded contextual region and the encoded background region is merged together to reconstruct the output image.