A SURVEY OF RECENT STUDIES INVESTIGATING THE POTENTIAL OF DEEP LEARNING ALGORITHMS FOR IDENTIFYING AND CATEGORIZING BREAST CANCER

Abstract

This paper provides a summary of recent investigations on the use of algorithms based on deep learning for detecting and classifying breast cancer, with the goal of improving timely diagnosis and treatment outcomes. Machine learning has an accuracy of 91% in identifying cancer, whereas human specialists have an accuracy of just 79%. In this study, we analyze and contrast the two most current machine learning algorithms for detecting and classifying breast cancer: RetinaNet and YOLO (You Only Look Once). This study adds support to the theory that machine learning-based technologies may be able to make more precise diagnoses of cancer than human doctors. When compared to other breast cancer screening and categorization systems using prominent public datasets, RetinaNet and YOLO fared the best.