BREAST CANCER PREDICTION USING ENSEMBLE MACHINE LEARNING MODELS AND FEATURE SELECTION

Abstract

Breast cancer detection has become a crucial area of research in medical imaging and artificial intelligence. Early detection significantly increases the chances of successful treatment and survival rates among patients. This study focuses on developing and implementing advanced machine learning and deep learning techniques to identify and classify breast cancer from mammographic and histopathological images. Techniques such as Convolutional Neural Networks (CNN), Support Vector Machines (SVM), and ensemble learning methods have demonstrated promising results in differentiating between malignant and benign tumors. The research emphasizes preprocessing methods like image enhancement, segmentation, and feature extraction to improve model accuracy. Datasets such as the Wisconsin Breast Cancer Dataset (WBCD) and the Digital Database for Screening Mammography (CBIS-DDSM) are widely used for model training and evaluation. The ultimate goal is to design a robust, automated diagnostic system that assists radiologists in early detection, reduces human error, and supports clinical decision-making for better healthcare outcomes.