Machine Learning for Early Breast Cancer Detection

Abstract

Abstract Globally, breast cancer (BC) remains a significant cause to female mortality. Early detection of BC plays an important role in reducing premature deaths. Various imaging techniques including ultrasound, mammogram, magnetic resonance imaging, histopathology, thermography, positron emission tomography, and microwave imaging have been employed for obtaining breast images (BIs). This review provides comprehensive information of different breast imaging modalities and publicly accessible BI sources. The advanced machine learning (ML) techniques offer a promising avenue to replace human involvement in detecting cancerous cells from BIs. The article outlines various ML algorithms (MLAs) which have been extensively used for identifying cancerous cells in BIs 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 BC identification and proposes potential solutions.