Modification of LBP for detecting liver cirrhosis from b-mode ultrasound image

Abstract

Liver cirrhosis is considered as one of the common most diseases in healthcare. The widely accepted technology for the diagnosis is ultrasound imaging. This paper presents such a technique for detecting the cirrhosis of liver through ultrasound images. The region of interest is selected from the ultrasound images that obtained from radiologist and then inspection technique is applied on it. The identification of liver cirrhosis from normal liver is finally detected through modified Local Binary Pattern (LBP) represented as Differential Local Binary Pattern (DLBP). The image intensities value of DLBP image were divided into five discriminating groups which were made by counting pixels of similar gray scale value. Decision of cirrhotic liver is given by the pixel values in all five groups. Experimental results from the proposed method demonstrated its feasibility and applicability for high performance cirrhotic liver identification.