An Explainable Transformer Model for Alzheimer's Disease Detection Using Retinal Imaging

2025-07-06

AI Summary

This study addresses the challenge of non-invasive early screening for Alzheimer’s disease (AD) by proposing Retformer—the first interpretable Transformer model designed for retinal multimodal imaging. Retformer jointly processes color fundus photographs, optical coherence tomography (OCT), and OCT angiography (OCTA) images, leveraging self-attention mechanisms to model cross-modal pathological correlations and integrating Grad-CAM for lesion-level visual interpretability. It simultaneously achieves high-accuracy AD classification—outperforming state-of-the-art methods by up to 11%—and biologically meaningful biomarker localization. For the first time, it systematically identifies AD-associated retinal regions across modalities, including thinning of the retinal nerve fiber layer and reduced microvascular density. These findings align closely with established clinical and neuropathological evidence, providing interpretable AI-driven validation of the retina as a non-invasive biomarker for AD.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Security and Privacy: Data transparency and provenance
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Alzheimer's disease (AD) is a neurodegenerative disorder that affects millions worldwide. In the absence of effective treatment options, early diagnosis is crucial for initiating management strategies to delay disease onset and slow down its progression. In this study, we propose Retformer, a novel transformer-based architecture for detecting AD using retinal imaging modalities, leveraging the power of transformers and explainable artificial intelligence. The Retformer model is trained on datasets of different modalities of retinal images from patients with AD and age-matched healthy controls, enabling it to learn complex patterns and relationships between image features and disease diagnosis. To provide insights into the decision-making process of our model, we employ the Gradient-weighted Class Activation Mapping algorithm to visualize the feature importance maps, highlighting the regions of the retinal images that contribute most significantly to the classification outcome. These findings are compared to existing clinical studies on detecting AD using retinal biomarkers, allowing us to identify the most important features for AD detection in each imaging modality. The Retformer model outperforms a variety of benchmark algorithms across different performance metrics by margins of up to 11.

Problem

• Detect Alzheimer's disease using retinal imaging
• Develop explainable AI model for early AD diagnosis
• Identify key retinal biomarkers for AD detection

Innovation

• Transformer-based architecture for AD detection
• Explainable AI with feature importance visualization
• Multi-modal retinal image training dataset