Leveraging Bi-Focal Perspectives and Granular Feature Integration for Accurate Reliable Early Alzheimer's Detection

2024-07-15

AI Summary

Conventional CNNs struggle to model subtle pathological hallmarks of Alzheimer’s disease (AD)—such as neurofibrillary tangles and amyloid plaques—hindering early, accurate AD detection from neuroimaging. Method: We propose a multi-scale granularity-cooperative modeling framework that jointly encodes macroscopic anatomical structures and microscopic pathological features. Our approach introduces a novel granularity-aware feature fusion mechanism and a dual-focus attention mechanism, embedded within an enhanced CNN architecture comprising a multi-scale feature pyramid, an attention-guided dual-focus enhancement module, and a cross-level granularity fusion strategy. Contribution/Results: On AD classification, our model achieves 99.31% F1-score, 99.24% precision, and 99.51% recall—significantly outperforming state-of-the-art CNN-based methods. The framework delivers improved interpretability and robustness, establishing a new paradigm for early, precise, and explainable AD diagnosis from medical imaging.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Being the most commonly known neurodegeneration, Alzheimer's Disease (AD) is annually diagnosed in millions of patients. The present medical scenario still finds the exact diagnosis and classification of AD through neuroimaging data as a challenging task. Traditional CNNs can extract a good amount of low-level information in an image while failing to extract high-level minuscule particles, which is a significant challenge in detecting AD from MRI scans. To overcome this, we propose a novel Granular Feature Integration method to combine information extraction at different scales along with an efficient information flow, enabling the model to capture both broad and fine-grained features simultaneously. We also propose a Bi-Focal Perspective mechanism to highlight the subtle neurofibrillary tangles and amyloid plaques in the MRI scans, ensuring that critical pathological markers are accurately identified. Our model achieved an F1-Score of 99.31%, precision of 99.24%, and recall of 99.51%. These scores prove that our model is significantly better than the state-of-the-art (SOTA) CNNs in existence.

Problem

• Early detection of Alzheimer's Disease
• Accurate classification from MRI scans
• Identifying subtle pathological markers in neuroimaging

Innovation

• Granular Feature Integration for multi-scale extraction
• Bi-Focal Perspective highlights pathological markers
• Efficient information flow captures broad features