Compression of MRI images using the discrete wavelet transform and improved parameter free Bayesian restoration techniques

Abstract

This paper suggests a novel MRI image compression scheme, using the discrete wavelet transformation (DWT) and an improved Bayesian restoration approach. The suggested methodology is based on preservation of important second order correlation (“textural”) features of either DWT coefficients or image pixel intensities. While rival image compression methodologies utilizing the DWT apply it to the whole original image uniformly, the herein presented novel approach involves a sophisticated DWT application scheme. That is, different compression ratios are applied to the wavelet coefficients belonging in the different regions of interest, in which either each wavelet domain band of the transformed image or the image itself is clustered, respectively, employing textural descriptors as criteria. Restoration of the original MRI image from its corresponding regions of interest compressed images involves the inverse DWT and a sophisticated Bayesian restoration approach which does not require user defined parameters, since all parameters are subject to the same optimization process. An experimental study is conducted to qualitatively assessing all approaches in comparison with the original DWT compression technique, when applied to a set of brain MRI images.