Counterfactual Explanations in Medical Imaging: Exploring SPN-Guided Latent Space Manipulation

TL;DR

This paper introduces a novel method using sum-product networks to generate plausible counterfactual explanations in medical imaging, improving interpretability of deep learning models by optimizing latent space manipulations.

Contribution

It proposes a new SPN-guided latent space approach for counterfactual generation, combining probabilistic modeling with deep generative models for better interpretability.

Findings

SPN-guided method produces more plausible counterfactuals.

Compared to neural network baseline, method improves explanation quality.

Trade-off analysis reveals optimal regularization for counterfactuals.

Abstract

Artificial intelligence is increasingly leveraged across various domains to automate decision-making processes that significantly impact human lives. In medical image analysis, deep learning models have demonstrated remarkable performance. However, their inherent complexity makes them black box systems, raising concerns about reliability and interpretability. Counterfactual explanations provide comprehensible insights into decision processes by presenting hypothetical "what-if" scenarios that alter model classifications. By examining input alterations, counterfactual explanations provide patterns that influence the decision-making process. Despite their potential, generating plausible counterfactuals that adhere to similarity constraints providing human-interpretable explanations remains a challenge. In this paper, we investigate this challenge by a model-specific optimization approach. While deep generative models such as variational autoencoders (VAEs) exhibit significant generative power, probabilistic models like sum-product networks (SPNs) efficiently represent complex joint probability distributions. By modeling the likelihood of a semi-supervised VAE's latent space with an SPN, we leverage its dual role as both a latent space descriptor and a classifier for a given discrimination task. This formulation enables the optimization of latent space counterfactuals that are both close to the original data distribution and aligned with the target class distribution. We conduct experimental evaluation on the cheXpert dataset. To evaluate the effectiveness of the integration of SPNs, our SPN-guided latent space manipulation is compared against a neural network baseline. Additionally, the trade-off between latent variable regularization and counterfactual quality is analyzed.