Seeing What Shouldn't Be There: Counterfactual GANs for Medical Image Attribution

2026-05-06

AI Summary

This work addresses the limitation of existing medical image attribution methods, which focus narrowly on minimal discriminative features while neglecting other salient anatomical structures, thereby failing to provide comprehensive and clinically trustworthy explanations. To overcome this, the authors propose a class-oriented counterfactual feature attribution framework that uniquely integrates counterfactual explanation with generative adversarial networks (GANs). By incorporating a cycle-consistency loss, the method generates realistic and semantically plausible counterfactual instances that effectively highlight lesion regions critical to model decisions. The study further introduces a reliable counterfactual generation mechanism alongside dedicated quality evaluation metrics, enabling analogical self-explanation. Experiments on synthetic data, tuberculosis datasets, and the BraTS benchmark demonstrate that the generated counterfactuals exhibit superior clinical plausibility and establish a new baseline on BraTS.

Abstract

Ascription of an image gives insights into the objects that influence the classification of the whole image or its pixels towards a specific category. These insights help radiologists to visualize deformities in medical imaging. Most of the existing visualization techniques are based on discriminative models and highlight regions of the input image participating in the decision-making of a classifier. However, these approaches do not take all noticeable objects into account as their objective is to classify the input by using a minimal set of discriminative features. To overcome the issue, a counterfactual explanation (CX) based class-oriented feature attribution method is proposed. A counterfactual explanation (CX) explicates a causal reasoning process of the form: "if X had not happened, then Y would not have happened". The method is built on generative adversarial networks (GANs) with a cyclical-consistent loss function. We evaluate our method on three datasets: synthetic, tuberculosis and BraTS. All experiments confirm the efficacy of the proposed method. This study also highlighted the limitations of existing counterfactual explanation techniques in producing plausible counterfactual instances (CIs). Accompanying CXs with believable CIs thus provides self-explanatory analogy-based explanations. To this end, a CI generation method is proposed. Also, a novel technique is used to evaluate the quality of CI. The baseline results are produced on the BraTS dataset.

Problem

• counterfactual explanation
• medical image attribution
• generative adversarial networks
• feature attribution
• counterfactual instances

Innovation

• Counterfactual Explanation
• Generative Adversarial Networks
• Medical Image Attribution
• Cycle-Consistent Loss
• Counterfactual Instances