A Quantitatively Interpretable Model for Alzheimer's Disease Prediction Using Deep Counterfactuals

TL;DR

This paper introduces a quantitatively interpretable deep learning framework for Alzheimer's disease prediction that uses counterfactual reasoning and structural MRI analysis to provide both accurate predictions and meaningful neuroscientific insights.

Contribution

It proposes a novel framework combining counterfactual reasoning with MRI analysis to enhance interpretability and achieve competitive predictive performance in AD diagnosis.

Findings

Framework produces an AD-relatedness index for brain regions.

Achieves predictive accuracy comparable to deep learning models.

Provides quantitative, neuroscientifically valid explanations.

Abstract

Deep learning (DL) for predicting Alzheimer's disease (AD) has provided timely intervention in disease progression yet still demands attentive interpretability to explain how their DL models make definitive decisions. Recently, counterfactual reasoning has gained increasing attention in medical research because of its ability to provide a refined visual explanatory map. However, such visual explanatory maps based on visual inspection alone are insufficient unless we intuitively demonstrate their medical or neuroscientific validity via quantitative features. In this study, we synthesize the counterfactual-labeled structural MRIs using our proposed framework and transform it into a gray matter density map to measure its volumetric changes over the parcellated region of interest (ROI). We also devised a lightweight linear classifier to boost the effectiveness of constructed ROIs, promoted quantitative interpretation, and achieved comparable predictive performance to DL methods. Throughout this, our framework produces an ``AD-relatedness index'' for each ROI and offers an intuitive understanding of brain status for an individual patient and across patient groups with respect to AD progression.