Title: A novel method for predicting kidney diseases using optimal artificial neural network in ultrasound images

Authors: S. Packirisamy Balamurugan; Gurusamy Arumugam

Addresses: Department of Computer and Information Science, Faculty of Science, Annamalai University, Chidambaram, India ' Department of Computer Science, Madurai Kamaraj University, Madurai, India

Abstract: The main aim of this research is to design and develop an efficient approach for predicting ultrasound kidney diseases using multiple stages. Nowadays, kidney disease prediction is one of the crucial procedures in surgical and treatment planning for ultrasound images. Therefore, in this paper, we propose a novel ultrasound kidney diseases prediction using the artificial neural network (ANN). To achieve the concept, we comprise the proposed system into four modules such as preprocessing, feature extraction, feature selection using OGOA and disease prediction using ANN. Initially, we eliminate the noise present in the input image using the optimal wavelet and bilateral filter. Then, a set of GLCM features are extracted from each input image and then we select the important features using oppositional grasshopper optimisation algorithm (OGOA). To classify the image as normal or abnormal, the proposed method utilises an artificial neural network (ANN). The performance of the proposed method is evaluated using accuracy, sensitivity, and specificity. The experimentation results show that the proposed system attains the maximum accuracy of 95.83% which is high compared to existing methods.

Keywords: ultrasound image; neural network; multi-kernel k-means clustering; GLCM features; segmentation; classification; bilateral filter; oppositional grasshopper optimisation algorithm; OGOA.

DOI: 10.1504/IJIE.2020.104644

International Journal of Intelligent Enterprise, 2020 Vol.7 No.1/2/3, pp.37 - 55

Received: 13 Jul 2018
Accepted: 25 Sep 2018

Published online: 24 Jan 2020 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article