Breast cancer (BC) is the second most common cause of fatality in females. Through their lifetime period, out of 8 females, 1 female (or roughly 13%) might get invasive BC. The survival rate of this possible fatal disorder improves when it is identified early, and treatment expenses are also decreased. Owing to advances in radiographic imaging, early detection of this fatal disease has become possible by using technologies like histopathological imaging (HI), 3D mammography, mammograms, positron emission tomography (PET)/computed tomography (CT), and MRI (Magnetic resonance imaging). The world has changed dramatically in the past ten years thanks to advances in machine learning (ML) and computer vision. Deep learning (DL), a branch of machine learning (ML) can manage massive amounts of data, it has demonstrated remarkable performance when assessed and applied for the detection and prediction of BC through the use of radiographic and histopathological images. This study's primary goal is to provide a critical examination of prior research and findings on the detection and classification of BC utilizing a variety of imaging techniques, such as Ultrasound, PET/CT, Mammography, Thermography, MRI, and Histopathology.