Breast cancer remains a major cause of cancer-related mortality among women, highlighting the need for reliable and early diagnostic tools. In this work, we propose a deep learning framework based on convolutional neural networks (CNNs) for automated classification of breast ultrasound (BUS) images. The framework processes raw images through preprocessing and augmentation steps, followed by a lightweight CNN designed to distinguish between normal, benign, and malignant cases. Experiments were conducted on the BUSI dataset, extended to 7,208 samples through augmentation. The proposed model achieved an accuracy of 92.3% and an AUC of 0.98–0.99, outperforming existing baselines and approaching expert-level performance. These results confirm the potential of CNN-based computer-aided diagnosis systems to support radiologists in clinical decision-making and improve early breast cancer detection.