DeepWolfNet Model: Enhancing Medical Disease Diagnosis Using Gray Wolf Technology and Deep Neural Networks

Abstract

Breast cancer occurs when cells or tissues of the breast grow abnormally. Globally, cancer is a common and serious disease, greatly affecting women. Recent studies aim to develop effective methods for deep recognition of medical images using deep neural networks (DNNs). In this context, the research presents a deep learning-based model using a DNN for breast cancer detection and is applied to two datasets, namely breast ultrasound images (BUSI) containing 780 images classified into benign, malignant, and normal, and the BreakHis-400X database. The images are processed using the gray wolf optimization (GWO) algorithm to extract the most important features. Medical image processing is a crucial step in improving classification accuracy, as the GWO algorithm helps improve the feature selection process by identifying the most important elements in images that directly affect the prediction accuracy, reducing the amount of unimportant data, and enhancing the efficiency of the deep learning model. The purpose of using GWO is to improve the effectiveness of feature extraction and avoid falling into local solutions, which contributes to significantly improving the classification accuracy. The proposed model, using the GWO algorithm with DNN, achieved high classification accuracy that outperformed traditional models such as support vector machines (SVM), VGG16, Googlenet, and KNN models.