Breast cancer diagnosis relies on accurate and interpretable models to aid in clinical decision-making. Traditional deep learning models, such as convolutional neural networks (CNNs), often exhibit high performance but lack interpretability, which is crucial in healthcare applications. To address this, we present an Attentive Convolutional Neuro-Fuzzy Network (ACNFN) designed to deliver both high diagnostic accuracy and transparency. The proposed ACNFN integrates fuzzy inference with an attention mechanism, enabling the model to dynamically identify and prioritize the most relevant tumor features for classification. Additionally, the convolutional architecture optimizes feature subset selection, reducing rule dimensionality and improving interpretability. The model is evaluated on the Wisconsin Diagnostic Breast Cancer (WDBC) dataset, demonstrating superior performance in classifying benign and malignant tumors while providing clear and actionable insights into the diagnostic process. These results highlight the potential of ACNFN as a reliable and interpretable diagnostic tool in medical applications.