CheXplaining in Style: Counterfactual Explanations for Chest X-rays using StyleGAN

TL;DR

This paper introduces a StyleGAN-based method called StyleEx for generating counterfactual explanations of chest X-ray diagnoses, helping to interpret deep learning models in medical imaging.

Contribution

It presents a novel approach using StyleGAN to produce counterfactual explanations and introduces EigenFind to improve computational efficiency.

Findings

Counterfactual explanations align with radiologists' assessments

EigenFind reduces explanation generation time significantly

Method enhances interpretability of chest X-ray classifiers

Abstract

Deep learning models used in medical image analysis are prone to raising reliability concerns due to their black-box nature. To shed light on these black-box models, previous works predominantly focus on identifying the contribution of input features to the diagnosis, i.e., feature attribution. In this work, we explore counterfactual explanations to identify what patterns the models rely on for diagnosis. Specifically, we investigate the effect of changing features within chest X-rays on the classifier's output to understand its decision mechanism. We leverage a StyleGAN-based approach (StyleEx) to create counterfactual explanations for chest X-rays by manipulating specific latent directions in their latent space. In addition, we propose EigenFind to significantly reduce the computation time of generated explanations. We clinically evaluate the relevancy of our counterfactual explanations with the help of radiologists. Our code is publicly available.