Performance Analysis of Classifiers for Liver Cirrhosis Detection Using Fast Hadamard-EHO Transform Features

Liver cirrhosis is a gradual and irreversible disorder that impairs liver function, frequently resulting in serious complications if not identified promptly. Conventional diagnostic approaches, including biopsies and imaging techniques, may be invasive, protracted, and necessitate specialist analysis. This research introduces a soft computing based technique for the detection of liver cirrhosis, utilizing sophisticated machine learning algorithms and medical imaging analysis. The method employs ultrasonic images, to detect cirrhotic patterns and categorize liver abnormalities. In this work the hybrid Fast Hadamard EHO techniques is used for feature extraction. The five classifiers such as Gaussian Mixture Model (GMM), Dragon Fly algorithm, Harmonic Search and hybrid algorithm such as Dragon fly GMM and Harmonic search GMM were used for classification of liver abnormality. The Hybrid classifier Harmonic GMM gives prominent accuracy of 96.43% and a minimum error rate of 3.57%.