الفهرس | Only 14 pages are availabe for public view |
Abstract Hepatic steatosis occurs when lipids accumulate in the liver and can eventually liver failure requiring a liver transplant. This work develop a computationally-efficient technique to classify fatty liver using B-mode us images. The technique relies on extracting features from the Wavelet domain using the approximation part of us images. Features include the first-order gray-level parameters, co-occurrence matrices, and local binary patterns. The technique was tested using mouse livers and image of human livers. This technique shall improve the implementation of manufacturer independent real time techniques for fatty liver classification |