medXGAN: Visual Explanations for Medical Classifiers through a Generative Latent Space

TL;DR

medXGAN is a novel generative adversarial framework that provides visual explanations for medical classifiers by disentangling anatomical structures and pathologies, improving interpretability and robustness in medical image analysis.

Contribution

This work introduces medXGAN, a new generative model that visually explains medical classifier decisions by leveraging domain knowledge and latent space interpolation.

Findings

Outperforms Grad-CAM and Integrated Gradients in localization accuracy.

Enables fine-grained visualization of anatomical and pathological features.

Combining medXGAN with Integrated Gradients enhances explanation robustness.

Abstract

Despite the surge of deep learning in the past decade, some users are skeptical to deploy these models in practice due to their black-box nature. Specifically, in the medical space where there are severe potential repercussions, we need to develop methods to gain confidence in the models' decisions. To this end, we propose a novel medical imaging generative adversarial framework, medXGAN (medical eXplanation GAN), to visually explain what a medical classifier focuses on in its binary predictions. By encoding domain knowledge of medical images, we are able to disentangle anatomical structure and pathology, leading to fine-grained visualization through latent interpolation. Furthermore, we optimize the latent space such that interpolation explains how the features contribute to the classifier's output. Our method outperforms baselines such as Gradient-Weighted Class Activation Mapping (Grad-CAM) and Integrated Gradients in localization and explanatory ability. Additionally, a combination of the medXGAN with Integrated Gradients can yield explanations more robust to noise. The code is available at: https://avdravid.github.io/medXGAN_page/.