Detection of Normal/ Abnormal Kidney Images by Using Artificial Neural Network with Fire Fly Algorithm

Abstract

Ultrasound (US) imaging is used to provide the structural abnormalities like stones, infections and cysts for kidney diagnosis and also produces information about kidney functions. The goal of this work is to classify the kidney images using US according to relevant features selection. In this work, images of a kidney are classified as abnormal images by pre-processing (i.e. grey-scale conversion), generate region-of-interest, extracting the features as multi-scale wavelet-based Gabor method, Fire Fly (FF) for optimization and Artificial Neural Network (ANN). The FF-ANN method is simulated on the platform of MATLAB and these results are evaluated and contrasted. The outcome of these results proved that the FF-ANNN had 100% specificity and 94% accuracy. By comparing it with the existing methods, the FF-ANN achieved 0% false-acceptance rate.