Explainable artificial intelligence (XAI) in deep learning-based medical image analysis

TL;DR

This survey reviews the application of explainable AI techniques in deep learning-based medical image analysis, emphasizing the importance of transparency for high-stakes medical decisions and categorizing existing methods.

Contribution

It introduces a framework for classifying XAI methods in medical imaging and provides a comprehensive survey of current techniques and future opportunities.

Findings

XAI methods are categorized by framework and anatomical location.

The survey highlights the importance of explainability in medical decision-making.

Future directions include developing more interpretable models and evaluation metrics.

Abstract

With an increase in deep learning-based methods, the call for explainability of such methods grows, especially in high-stakes decision making areas such as medical image analysis. This survey presents an overview of eXplainable Artificial Intelligence (XAI) used in deep learning-based medical image analysis. A framework of XAI criteria is introduced to classify deep learning-based medical image analysis methods. Papers on XAI techniques in medical image analysis are then surveyed and categorized according to the framework and according to anatomical location. The paper concludes with an outlook of future opportunities for XAI in medical image analysis.