Unlocking the Potential Thorough Analysis of Machine Learning for Breast Cancer Diagnosis

Abstract

To forecast breast cancer with the goal of giving a thorough rundown of current developments in the area. Given that breast cancer is among the world's leading causes of mortality for women; improving patient outcomes requires early detection. This study looks into the ability to predict outcomes using a variety of machine learning (ML) models, including random forests, logistic regression, support vector machines, decision trees, k- nearest neighbours, and deep learning neural networks, in predicting the incidence of breast cancer from patient data, including genetic markers, imaging results, and demographics. Aims to provide a comprehensive analysis of presetn advancements, obstacles, and prospects in the field of CNN-based techniques for breast cancer identification. The review begins by outlining the urgent need for reliable and accurate diagnostic methods for breast cancer, highlighting the critical role that early identification plays in enhancing patient outcomes. Which delves into the intricate architecture of CNNs, revealing its unique applicability to mammography image analysis as well as their innate advantages in image classification tasks. Important topics of discussion include the various CNN architectures used for two- and three- dimensional (2D) imaging methods used in breast cancer diagnosis.