Breast Cancer Detection Framework using Evolutionary Search and SVM Classifier

Abstract

Because breast cancer is a common and potentially dangerous disease, early and correct detection is essential for effective treatment. The present research paper, we propose a breast cancer detection framework that combines evolutionary search algorithms and Support Vector Machine (SVM) classifiers help to increase the accuracy and effectiveness of diagnosis.The framework utilizes evolutionary search algorithms to optimize the selection of relevant features from medical imaging data, followed by classification using SVM classifiers. The evolutionary search algorithms aid in identifying the most discriminative features, while the SVM classifiers provide efficient and accurate classification based on these features. By integrating these techniques, the proposed framework offers a comprehensive and automated approach to breast cancer detection. The usefulness of the proposed framework is demonstrated by experimental findings on benchmark datasets, achieving high classification accuracy and outperforming existing methods. The proposed framework has an opportunity to advance development of advanced breast cancer diagnostic tools, Enabling early detection and prompt intervention, increasing patient outcomes is the end goal and reducing mortality rates.