Survey and Current Research Challenges for Breast Cancer Detection

What is it about?

The paper examines various techniques for early breast cancer detection, crucial for improving prognosis and quality of life. It evaluates machine learning (ML) and deep learning (DL) approaches, including optimization, preprocessing, and transfer learning, highlighting their advantages and limitations. The study reviews ML techniques like Support Vector Machine (SVM) and Multilayer Perceptron (MLP), noting their efficacy on datasets such as the Wisconsin Diagnostic Breast Cancer (WDBC) dataset. It also discusses feature selection methods and preprocessing techniques that enhance image analysis. Deep learning models, particularly those using convolutional neural networks (CNNs), show promise in improving detection accuracy, with transfer learning optimizing these models further. Despite advancements, the study identifies challenges such as false positives/negatives and data sparsity, emphasizing the need for robust, real-world applicable detection systems to enhance early and accurate diagnosis.

Featured Image

Photo by National Cancer Institute on Unsplash

Photo by National Cancer Institute on Unsplash