Survey on Novel Approaches of Efficient Algorithms for Breast Cancer Detection

Abstract

Breast cancer remains one of the leading causes of mortality among women worldwide, necessitating the development of efficient and accurate detection algorithms. This survey examines novel approaches in breast cancer detection algorithms, focusing on machine learning and deep learning methodologies that have emerged in recent years. The study analyses various algorithmic approaches including SVM, Random Forest, CNN, and hybrid models that combine multiple techniques for enhanced accuracy. Through comprehensive analysis of secondary and primary data from multiple studies, this research identifies that ANN achieve the highest accuracy rates of 98.57% in breast cancer classification tasks. The survey also explores the integration of explainable AI techniques that provide transparency in decision-making processes, crucial for medical applications. Recent developments in deep learning architectures, particularly CNN-based models, demonstrate significant improvements in mammographic image analysis with accuracies reaching 91.67%. The findings indicate that ensemble methods and feature engineering approaches show promising results in improving detection sensitivity and specificity. This comprehensive review provides insights into current algorithmic trends, performance metrics, and future directions in breast cancer detection technology.