A New NSCT Based Contrast Enhancement Algorithm for Amplification of Early Signs of Ischemic Stroke in Brain CT Images

Brain CT images are extensively used in detection of Cerebrovascular Accidents (CVA). But CT scan is not really a sensitive test for diagnosis of ischemic stroke. Most of the times, early CT images barely show or even don ´t show any noticeable sign of ischemia. But it is possible to put emphasis on subtle signs of ischemia by means of image contrast enhancement. Contrast enhancement using multiscale transforms is one of the most popular approaches in recent years. Nonsubsampled Contourlet Transform (NSCT) is a directional multiscale transform that is able to take geometrical structures into account. In this paper we are about to customize this transform and improve its performance in contrast enhancement of brain CT images. To this end, we propose a set of simpler and more efficient filters for Nonsubsampled Pyramid (NSP) and introduce an improved method for modification of directional subbands´ coefficients.