Counterfactual Explanation of Brain Activity Classifiers using Image-to-Image Transfer by Generative Adversarial Network

TL;DR

This paper introduces a novel generative model called CAG that provides counterfactual explanations for brain activity classifiers, enabling better understanding of neural decision-making and revealing subtle brain activity patterns.

Contribution

The paper presents a new generative DNN for counterfactual explanation of brain activity classifiers, capable of handling multiple class transformations and enhancing interpretability.

Findings

CAG effectively explains classifiers for seven behavioral tasks.

Iterative CAG application reveals subtle brain activity patterns.

Counterfactual image-to-image transformation aids understanding of DNN decisions.

Abstract

Deep neural networks (DNNs) can accurately decode task-related information from brain activations. However, because of the nonlinearity of the DNN, the decisions made by DNNs are hardly interpretable. One of the promising approaches for explaining such a black-box system is counterfactual explanation. In this framework, the behavior of a black-box system is explained by comparing real data and realistic synthetic data that are specifically generated such that the black-box system outputs an unreal outcome. Here we introduce a novel generative DNN (counterfactual activation generator, CAG) that can provide counterfactual explanations for DNN-based classifiers of brain activations. Importantly, CAG can simultaneously handle image transformation among multiple classes associated with different behavioral tasks. Using CAG, we demonstrated counterfactual explanation of DNN-based classifiers that learned to discriminate brain activations of seven behavioral tasks. Furthermore, by iterative applications of CAG, we were able to enhance and extract subtle spatial brain activity patterns that affected the classifier's decisions. Together, these results demonstrate that the counterfactual explanation based on image-to-image transformation would be a promising approach to understand and extend the current application of DNNs in fMRI analyses.