Comparison of deep learned and texture features in mammographic mass classification

Abstract

As deep learning models are increasingly applied in medical diagnostic assistance systems, this raises questions about ones ability to understand and interpret its decision-making process. In this work, using breast lesions from the Optimam Mammography Image Database (OMI-DB), we have explored whether deep learned features have similar predictive information as classical texture features. We trained a deep learning model for mass lesion classification and used Gradient-weighted Class Activation Mapping to produce a representation of deep learned features. Additional, classical texture features (e.g. energy) were extracted. Subsequently, we used the earth mover’s distance to investigate similarities between deep learned and texture features. The comparison identified that texture features such as mean, entropy and auto-correlation showed a strong similarity with the deep learned features and provided an indication of what the deep learning models might have used as information for its classification.