Machine Learning for Early Breast Cancer Detection

Abstract

Globally, breast cancer remains a significant cause to female mortality. Early detection plays a crucial role in reducing premature deaths. Various imaging techniques, including ultrasound, mammogram, magnetic resonance imaging, histopathology, thermography, positron emission tomography, and microwave imaging, have been explored for obtaining breast images. This review article delves into the details of different breast imaging modalities and publicly accessible sources of breast images. The advanced machine learning (ML) technique offers a promising avenue to replace human involvement in detecting cancerous cells from breast images. The article outlines various ML algorithms (MLAs) extensively employed for identifying cancerous cells in images at the early stages, categorizing them based on the presence or absence of malignancy. Additionally, the review addresses current challenges associated with the application of MLAs in breast cancer identification and proposes potential solutions.