Metastatic Breast Cancer Detection Using Deep Learning Algorithms: A Systematic Review

Abstract

Breast cancer (BC) is a pervasive issue that leads to countless fatalities among women worldwide, and metastatic breast cancer is responsible for most of these deaths. Early detection of metastatic BC is essential for improving patient outcomes and increasing survival rates. There have been a lot of earlier Machine Learning (ML)-based investigations. Decision trees (DT), K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Naive Bayes (NB), and other ML procedures achieve better in their corresponding fields. However, current methods for detecting metastatic BC can be time-consuming, invasive, and costly. Recently, deep learning (DL) algorithms have shown great potential in improving the accuracy and efficiency of BC detection. This paper delivers an inclusive systematic review (SR) of the existing research on using DL algorithms for metastatic BC detection. The article highlights the potential of DL algorithms in improving BC detection and the challenges associated with their use. Future research should address these challenges to improve the clinical utility of DL algorithms for metastatic BC detection.