Identifying Alzheimer's Disease Prediction Strategies of Convolutional Neural Network Classifiers using R2* Maps and Spectral Clustering

TL;DR

This paper investigates how different preprocessing and training choices influence deep learning classifiers for Alzheimer's disease using R2* maps, employing spectral clustering and interpretability methods to reveal decision strategies.

Contribution

It introduces a spectral clustering approach combined with Layer-wise Relevance Propagation to analyze and compare decision strategies of CNN classifiers in AD diagnosis.

Findings

Spectral clustering identified distinct decision patterns in classifiers.

Relevance heatmaps aligned with subject groups, improving interpretability.

Preprocessing and training choices significantly affect model decision strategies.

Abstract

Deep learning models have shown strong performance in classifying Alzheimer's disease (AD) from R2* maps, but their decision-making remains opaque, raising concerns about interpretability. Previous studies suggest biases in model decisions, necessitating further analysis. This study uses Layer-wise Relevance Propagation (LRP) and spectral clustering to explore classifier decision strategies across preprocessing and training configurations using R2* maps. We trained a 3D convolutional neural network on R2* maps, generating relevance heatmaps via LRP and applied spectral clustering to identify dominant patterns. t-Stochastic Neighbor Embedding (t-SNE) visualization was used to assess clustering structure. Spectral clustering revealed distinct decision patterns, with the relevance-guided model showing the clearest separation between AD and normal control (NC) cases. The t-SNE visualization confirmed that this model aligned heatmap groupings with the underlying subject groups. Our findings highlight the significant impact of preprocessing and training choices on deep learning models trained on R2* maps, even with similar performance metrics. Spectral clustering offers a structured method to identify classification strategy differences, emphasizing the importance of explainability in medical AI.