A combinatorial deep learning method for Alzheimer's disease classification-based merging pretrained networks.

Area of Science:

• Neuroscience
• Artificial Intelligence
• Medical Imaging

Background:

• Alzheimer's disease (AD) is a progressive neurodegenerative disorder with significant impact on cognitive function and daily life.
• Early diagnosis and intervention are crucial for effective Alzheimer's disease management, yet current methods face limitations.
• Pretrained convolutional neural networks (CNNs) show promise for AD classification using medical images.

Purpose of the Study:

• To introduce a novel hybrid deep learning model for enhanced Alzheimer's disease detection.
• To improve the accuracy and robustness of AD classification from MRI images.
• To provide a more reliable tool for early diagnosis and monitoring of Alzheimer's disease progression.

Main Methods:

• A hybrid deep learning approach combining two pretrained CNN architectures was developed.
• The model leverages the feature extraction capabilities of both networks to enhance AD-related pattern representation.
• Validation was performed on a large dataset of MRI images from Alzheimer's disease patients, with performance evaluated against noise and other models.

Main Results:

• The proposed hybrid model achieved a classification accuracy rate of 99.85%.
• The model demonstrated significant performance improvements compared to individual pretrained models.
• Comparative analysis confirmed the superiority of the hybrid architecture in classification rate and noise resistance.

Conclusions:

• The high accuracy and robustness of the hybrid model indicate its strong potential for early Alzheimer's disease detection.
• This AI-driven approach can assist clinicians in making more reliable early diagnoses and monitoring disease progression.
• The developed model offers a promising advancement for better Alzheimer's disease management through timely intervention.