ALOA: Ant Lion Optimization Algorithm-based Deep Learning for Breast Cancer Classification
Jack Russel Fernandis
Abstract
Normally, breast cancer is the most familiar disease, and it is the second leading type of cancer death among women. Breast cancer disease begins in malignant stage and it slowly develops from breast cell. Periodic clinical checks and self-tests assist for early prediction of breast cancer, thus the survival rate can increase significantly. In this paper, Ant Lion Optimization (ALO)-based Deep Neural Network (DNN) technique is developed for breast cancer classification. Here, the Type 2 Fuzzy and Cuckoo Search (T2FCS) method is utilized for pre-processing the input image. The color-based thresholding scheme is employed for segmenting the blood cells from the input breast cancer image. Furthermore, the statistical features are extracted from an input image for predicting breast cancer. Besides, the cancer classification is performed using a DNN classifier. The ALO algorithm is developed in this method to train the classifier for better performance. In addition, the developed breast cancer classification approach achieves a better classification performance based on several parameters, such as specificity, accuracy, and sensitivity. Thus, the developed ALO-based DNN method obtained enhanced results with high accuracy of 95.34%, sensitivity of 97.54%, and specificity of 95.34%.