Accurate and Efficient Algorithm for Detection of Alzheimer Disability Based on Deep Learning.

Area of Science:

• Neuroscience
• Artificial Intelligence
• Medical Imaging Analysis

Background:

• Alzheimer's Disease (AD) is a progressive neurodegenerative disorder impacting cognition and memory.
• Early AD detection is critical for effective intervention and improved patient outcomes.
• Traditional diagnostic methods like MRI and PET scans are expensive and not widely accessible.

Purpose of the Study:

• To develop an automated, cost-effective digital diagnostic approach for early AD identification and classification.
• To leverage deep learning (DL) and computer-aided detection (CAD) for improved diagnostic accessibility.
• To create a reliable tool for timely Alzheimer's Disease diagnosis and treatment planning.

Main Methods:

• Utilized pretrained convolutional neural networks (CNNs) for feature extraction.
• Integrated multi-class support vector machine (MSVM) and artificial neural network (ANN) classifiers.
• Employed a texture-based algorithm for feature reduction to enhance efficiency.

Main Results:

• Achieved high performance with 91% accuracy, 95% precision, and 90% recall.
• Identified seven key texture features for differentiating normal cases from mild AD stages.
• Validated the robustness and efficacy of the proposed DL-based CAD system.

Conclusions:

• Presents a reliable and affordable solution for early AD detection and diagnosis.
• The system demonstrates superior performance compared to existing state-of-the-art models.
• Suggests future research on larger datasets and integration with other imaging modalities for enhanced precision.