In this project the potential of Deep Learning methods for breast cancer classification was explored by applying Convolutional Neural Networks (CNNs) to classify normal, benign, and malignant breast tissue in mammograms. To shed light on the CNN's 'black-box' predictions, several post-hoc interpretability techniques were applied to gain insights into the decision-making process of CNNs. Moreover, a new dataset of preprocessed mammograms was created as part of this research Preprocessed Data See link to paper: https://proceedings.mlr.press/v248/balve24a.html