Resumen
Breast cancer was diagnosed in 2.3 million women, and around 685,000 deaths from breast cancer were recorded globally in 2020, making it the most common cancer. Early and accurate detection of breast cancer plays a critical role in improving the prognosis and bringing the patient survival rate to 50%. Deep learning-based computer-aided diagnosis (CAD) has achieved remarkable performance in early breast cancer diagnosis. This review focuses on literature considering deep learning architecture for breast cancer diagnosis. Therefore, this study anchors a well systematic and analytical review from six aspects: the model architecture of breast cancer diagnosis, datasets and image pre-processing, the manner of breast-cancer imaging, performance measurements, and research directions.