Alzheimer's Disease detection and classification using optimized neural network.

Area of Science:

• Neurology
• Artificial Intelligence
• Medical Imaging

Background:

• Alzheimer's disease (AD) is a neurodegenerative disorder causing cognitive decline.
• Early and accurate AD diagnosis is crucial for effective treatment and improved patient outcomes.

Purpose of the Study:

• To develop a novel approach for Alzheimer's disease (AD) detection using Deep Reinforcement Learning (DRL) and a Moth Flame Optimized Recurrent Neural Network (MFORNN).
• To enhance the accuracy and efficiency of AD identification from brain MRI scans.

Main Methods:

• Brain MRI samples were preprocessed to remove noise and enhance quality.
• The Moth Flame Optimization (MFO) algorithm was employed for feature selection from MRI images.
• Recurrent Neural Networks (RNNs) were utilized to learn temporal patterns, with parameters fine-tuned by Deep Reinforcement Learning (DRL).
• The framework was implemented using Python.

Main Results:

• The proposed DRL-MFORNN algorithm achieved high performance metrics: 99.31% accuracy, 99.24% precision, 99.43% recall, and 99.35% f-measure.
• Comparative analysis demonstrated the superior performance of the proposed technique over conventional classification algorithms.

Conclusions:

• The DRL-MFORNN approach offers a highly accurate and efficient method for Alzheimer's disease detection.
• This novel framework shows significant potential for clinical application in early AD diagnosis.