Artificial Neural Networks Interpretation Using LIME for Breast Cancer Diagnosis

Breast Cancer (BC) is the most common type of cancer among women. Thankfully early detection and treatment improvements helped decrease its number of deaths. Data Mining techniques (DM), which discover hidden and potentially useful patterns from data, particularly for breast cancer diagnosis, are witnessing a new era, where the main objective is no longer replacing humans or just assisting them in their tasks but enhancing and augmenting their capabilities and this is where interpretability comes into play. This paper aims to investigate the Local Interpretable Model-agnostic Explanations (LIME) technique to interpret a Multilayer perceptron (MLP) trained on the Wisconsin Original Data-set. The results show that LIME explanations are a sort of real-time interpretation that helps understanding how the constructed neural network "thinks" and thus can increase trust and help oncologists, as the domain experts, learn new patterns.