According to GLOBOCAN 2020, breast cancer is the most prevalent
cancer and affects many women globally after lung cancer. Detecting and
diagnosing breast cancer earlier may decrease the disease’s death rate.
A radiologist can use computer-aided detection/diagnosis technologies to
help make an early diagnosis of breast cancer. One of the most popular
and efficient techniques for identifying and diagnosing breast cancer is
mammography. Deep learning architectures called convolutional neural
network (CNN) models were developed to classify breast cancer correctly.
This paper presents breast cancer classification using a customized
deep-learning model. Two custom CNN models are suggested to classify the
breast cancer mammography image efficiently. The effectiveness of the
suggested classification approach was assessed using three real-time
datasets: MIAS, CBIS-DDSM, and INbreast. The outcomes demonstrate that
the suggested approach efficiently classifies the image and achieves
98.78%, 96.92%, and 97.84% accuracy for MIAS, CBIS-DDSM, and INbreast
datasets.