Deep CNN and Machine Learning Methods For Breast Cancer classification: A Review
Ramesh Vaishya, Praveen Kumar Shukla · 2024
Breast cancer is still a major global health concern, underscoring the critical need for precise and effective diagnostic techniques. This thorough review paper explores recent developments in breast cancer detection methodologies, with a particular emphasis on the use of transfer learning in conjunction with convolutional neural networks (CNNs), spiking neural networks (SNNs), and conventional machine learning algorithms. We also analyse a variety of approaches and methodologies utilized in recent research endeavours aimed at improving breast cancer detection. Using a variety of imaging modalities such as MRI, mammography, ultrasound, and histology images, we examine how well these approaches can improve the precision and effectiveness of diagnosis. We demonstrate, via painstaking analysis, that transfer learning is a key strategy for utilizing prior knowledge from various domains to enhance model performance in breast cancer diagnosis. Furthermore, we investigate alternative approaches like novel CNN architectures and hierarchical ML-based classification, offering insights into their contributions to the field. The importance of using transfer learning and other cutting-edge methods in breast cancer detection research is highlighted by our review, which ultimately aims to improve patient outcomes and diagnostic accuracy.