Interpretable Medical Image Classification using Prototype Learning and Privileged Information
This addresses the problem of interpretability in medical imaging for clinicians, offering an incremental improvement by combining existing techniques with privileged information.
The paper tackles the need for interpretable and high-performance medical image classification by proposing Proto-Caps, which uses capsule networks, prototype learning, and privileged information. On the LIDC-IDRI dataset, it achieves over 6% higher accuracy than baselines, reaching 93.0% for malignancy prediction, while providing visual prototype-based explanations.
Interpretability is often an essential requirement in medical imaging. Advanced deep learning methods are required to address this need for explainability and high performance. In this work, we investigate whether additional information available during the training process can be used to create an understandable and powerful model. We propose an innovative solution called Proto-Caps that leverages the benefits of capsule networks, prototype learning and the use of privileged information. Evaluating the proposed solution on the LIDC-IDRI dataset shows that it combines increased interpretability with above state-of-the-art prediction performance. Compared to the explainable baseline model, our method achieves more than 6 % higher accuracy in predicting both malignancy (93.0 %) and mean characteristic features of lung nodules. Simultaneously, the model provides case-based reasoning with prototype representations that allow visual validation of radiologist-defined attributes.