 This paper proposes a novel approach to breast cancer classification using meta-learning and multiple convolutional neural networks, CNNs. First, the BUSY dataset was pre-processed and divided into training and testing sets. Next, multiple CNNs were trained on the training set using different architectures and pre-trained models. These models were then evaluated on the test set and combined using a meta-ensemble algorithm. The evaluation results showed that the proposed model outperformed state-of-the-art approaches in terms of accuracy, precision, recall, and F1 score. This article was authored by Mohamed Danish Ali, Adnan Salim, Habib Elahi, and others.