Alzheimer's Disease Prediction Using Fly-Optimized Densely Connected Convolution Neural Networks Based on MRI Images.

Area of Science:

• Neuroscience and Artificial Intelligence
• Medical Imaging and Diagnostics

Background:

• Alzheimer's Disease (AD) is a progressive neurodegenerative disorder impacting memory and cognition, affecting millions globally.
• Current diagnostic methods for AD struggle with large datasets from region of interest (ROI) and biomarker identification.
• Machine learning offers potential for automated AD detection, but requires advanced techniques for complex pattern recognition in medical images.

Purpose of the Study:

• To develop an automated method for detecting Alzheimer's Disease-affected regions using metaheuristic-tuned deep learning.
• To enhance the early and accurate diagnosis of AD through advanced image processing and deep learning techniques.
• To improve patient outcomes and facilitate prompt therapeutic interventions for Alzheimer's Disease.

Main Methods:

• Utilized deep learning and image processing for AD detection, focusing on magnetic resonance imaging (MRI) scans.
• Employed an adaptive histogram approach for image processing and a weighted median filter to address noisy pixels.
• Implemented a deep convolution network-based clustering segmentation for issue region identification and correlated information theory for feature extraction.
• Applied fly-optimized densely linked convolution neural networks for probing selected features.

Main Results:

• The proposed method demonstrated superior performance compared to state-of-the-art techniques on the Kaggle dataset.
• Achieved significant improvements in sensitivity (15.52%), specificity (15.62%), accuracy (9.01%), error rate (11.29%), and F-measure (10.52%) for AD region recognition.
• Successfully identified subtle aberrations and complex alterations in brain structure indicative of AD.

Conclusions:

• Metaheuristic-tuned deep learning offers a powerful approach for the automated detection of Alzheimer's Disease.
• The developed method enhances early and accurate AD diagnosis by effectively analyzing MRI scans.
• This advancement holds promise for improving patient management and treatment strategies for Alzheimer's Disease.