Detection of cirrhosis through ultrasound imaging

Abstract

Cirrhosis is a liver disease that is considered to be among the most common diseases in healthcare. Due to its non-invasive nature, Ultrasound (US) imaging is a widely accepted technology for the diagnosis of this disease. This research work proposed a method for discriminating the cirrhotic liver from normal liver through US images. The liver US images were obtained from the radiologist. The radiologist also specified the Region of Interest (ROI) from these images and then the proposed method was applied on it. Two parameters were extracted from the US images through differences in intensity of neighboring pixels. Then these parameters can be used to train a classifier by which cirrhotic region of test patient can be detected. A 2-D array was created by difference in intensity of the neighboring pixels. From this array, two parameters were calculated. The decision was taken by checking these parameters. The validation of the proposed tool was done on 80 images of cirrhotic and 30 images of normal liver and classification accuracy of 98.18% was achieved. The result was also verified by the radiologist. The results verified its possibility and applicability for high performance cirrhotic liver discrimination.