Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methods

TL;DR

This review discusses various interpretability methods for deep neural networks in medical image analysis, emphasizing the importance of transparency for trustworthy AI in clinical applications.

Contribution

It systematically categorizes nine interpretability methods and evaluates progress, limitations, and future directions for explainability in medical imaging AI.

Findings

Nine types of interpretability methods identified

Progress in evaluating explanation quality reported

Guidelines and future directions discussed

Abstract

Artificial Intelligence has emerged as a useful aid in numerous clinical applications for diagnosis and treatment decisions. Deep neural networks have shown same or better performance than clinicians in many tasks owing to the rapid increase in the available data and computational power. In order to conform to the principles of trustworthy AI, it is essential that the AI system be transparent, robust, fair and ensure accountability. Current deep neural solutions are referred to as black-boxes due to a lack of understanding of the specifics concerning the decision making process. Therefore, there is a need to ensure interpretability of deep neural networks before they can be incorporated in the routine clinical workflow. In this narrative review, we utilized systematic keyword searches and domain expertise to identify nine different types of interpretability methods that have been used for understanding deep learning models for medical image analysis applications based on the type of generated explanations and technical similarities. Furthermore, we report the progress made towards evaluating the explanations produced by various interpretability methods. Finally we discuss limitations, provide guidelines for using interpretability methods and future directions concerning the interpretability of deep neural networks for medical imaging analysis.