AHANet: Adaptive Hybrid Attention Network for Alzheimer's Disease Classification Using Brain Magnetic Resonance...

Area of Science:

• Medical image processing
• Neurological disorders
• Artificial intelligence in healthcare

Background:

• Alzheimer's disease (AD) is a progressive neurological condition characterized by brain atrophy, memory loss, and cognitive decline.
• Early and accurate detection of AD is critical for effective treatment and management.
• Medical image processing, particularly analyzing brain Magnetic Resonance Imaging (MRI), presents challenges in identifying subtle signs of AD.

Purpose of the Study:

• To develop an advanced deep learning model for accurate and early detection of Alzheimer's disease using brain MRI.
• To enhance feature extraction capabilities for improved classification performance in AD diagnosis.

Main Methods:

• Proposed the Adaptive Hybrid Attention Network (AHANet), integrating Enhanced Non-Local Attention (ENLA) and Coordinate Attention modules.
• ENLA module captures global spatial and contextual features, including long-range dependencies.
• Coordinate Attention module extracts local features and embeds positional information into channel attention.
• An Adaptive Feature Aggregation (AFA) module fuses global and local features.
• The network architecture is built upon the DenseNet framework.
• Trained and validated the model on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset.

Main Results:

• The AHANet demonstrated superior performance compared to existing methods.
• Achieved a high classification accuracy of 98.53% for AD detection.
• The combined attention mechanisms and feature aggregation effectively boosted the network's feature extraction power.

Conclusions:

• The proposed AHANet offers a promising approach for accurate and early Alzheimer's disease detection from brain MRI.
• The integration of specialized attention modules and adaptive feature fusion significantly enhances diagnostic capabilities.
• This advancement in medical image analysis can aid clinicians in timely diagnosis and treatment planning for AD patients.