Simple Method to Enhance Ct Brain Images for Use in Diagnosis of Acute Cerebral Artery Infarction

In this paper we propose a simple method aiming at improving the visibility of the loss of the gray-white matter interface in computer tomography (CT) brain images. The loss of the gray-white matter interface is one of the early signs of acute cerebral artery infarction (ACAI). The method is to employ our proposed adaptive smoothing filter (ASF) to reduce local noise with edges preserved in CT brain images. The ASF is a specially designed filter with adaptive size and shape depending on local pixel-valuerelated information surrounding the pixel of interest. In order to demonstrate the superiority of the ASF, two commonly used filters for image smoothing, i.e., the averaging filter and the median filter were used for comparison. Two criteria, standard deviation and slope ratio, were adopted in this study for performance assessment. Moreover, the ASF was also applied to clinical CT brain images in hyperacute stroke patients for performance evaluation. Our preliminary results showed that the detectability of early infarct signs is much improved. The results demonstrate the superiority of the proposed method and its usefulness.