Influence of grey wolf optimization feature selection on gradient boosting machine learning techniques for accurate detection of liver tumor

Abstract

Malignant growth in liver results in liver tumor. The most common types of liver cancer are primary liver disease and secondary liver disease. Most malignant growths are benign tumors, and the condition they cause, essential liver disease, is the end result. Cancer of the liver is a potentially fatal disease that can only be cured by combining a number of different treatments. Machine learning, feature selection and image processing have the capability to provide a framework for the accurate detection of liver diseases. The processing of images is one of the components that come together to form this group. When utilized for the purpose of reviewing previously recorded visual information, the instrument performs at its highest level of effectiveness. The importance of feature selection on machine learning algorithms for the early and accurate diagnosis of liver tumors is discussed in this article. The input consists of images from a CT scan of the liver. These images are preprocessed by discrete wavelet transform. Discrete wavelet transforms increase resolution by compressing the images. Images are segmented in parts to identify region of interest by K Means algorithm. Features are selected by grey wolf optimization technique. Classification is performed by Gradient boosting, support vector machine and random forest. GWO Gradient boosting is performing better in accurate classification and prediction of liver cancer.