On segmentation of MR images using curvelet and Fuzzy C-means under compressed sensing

Medical image segmentation is a very difficult and challenging task due to many inherent complex characteristics, like differences in intensity values over an organ, presence of non-uniform large and small numbers of objects with missing and/or imprecise boundaries etc present in it. In many practical situations, medical images are captured at low measurement spaces i.e. at compressed sensing (CS) paradigm for a variety of reasons, for example, due to the limited number of sensors used or measurements may be extremely expensive. Reconstructed medical images after CS operation are found to have uneven intensity values as well as blurred non-uniform shape of the organs. Although, discrete wavelet based methods are widely used for edge enhancement and detection, but may not be efficient for detecting the curvatures of the different small organs. Curvelet, which is a multiscale multiresolution transform, can be used in segmentation of medical images rich with curvatures. In the proposed work, first a Magnetic Resonance (MR) image reconstruction at multi channel CS platform is done using a weighted fusion rule. Curvelet transform is then applied on MR images to obtained detailed image by suppressing the approximate subband. A sharpen image is formed which is then used for clustering, based on intensity values, using Fuzzy C-Means (FCM). Extensive simulation results are shown to highlight the performance improvement by the proposed method.