A New Quantitative Metric for Liver Classification from Ultrasound Images

Abstract

This paper presents a new quantitative metric which can be used as indirect method for characterization of liver from ultrasound images. This new metric is inspired from the visual criterion considered by the radiologists through texture and echogenicity of the Liver in ultrasound image. The proposed metric is a single parameter extracted from 6 texture features on the basis of Homogeneity, Roughness, Contrast, Granularity and Orientation of the liver surface for classification into Fatty or Normal liver. The main contribution of the present work is that the best texture features are selected on the basis of Fisher's linear discriminative analysis and then formulated into a single metric by considering their weightage similar to the visual criterion used for liver classification.