Explainable artificial intelligence in medical imaging: how to interpret, evaluate, and use artificial intelligence explanations.
TL;DR
An accessible overview of XAI is provided, including saliency maps, perturbation-based and feature-attribution approaches, concept- based methods, and example-based reasoning, as well as uncertainty quantification as a complementary approach for assessing prediction reliability, along with common misconceptions and emerging regulatory obligations.
Abstract
Most artificial intelligence (AI) models used in radiology are black boxes-they produce predictions without explaining the basis of their outputs, raising concerns about clinical safety, accountability, and trust. To address this, a growing body of methods has been developed to help clinicians understand and evaluate AI predictions. This field, known as explainable AI (XAI), aims to help clinicians interrogate, interpret, and critically evaluate AI predictions by identifying factors associated with model outputs. In this educational and practical review, we provide an accessible overview of XAI tailored for practicing radiologists and physicians. We cover the major categories of explanation methods, including saliency maps, perturbation-based and feature-attribution approaches, concept- based methods, and example-based reasoning, as well as uncertainty quantification as a complementary approach for assessing prediction reliability, along with common misconceptions and emerging regulatory obligations. We aim to make XAI easier for healthcare professionals to understand, as effective oversight of AI tools has become a core competency for the modern radiologist.