A³C-TL-GTO: Alzheimer Automatic Accurate Classification Using Transfer Learning and Artificial Gorilla Troops...

Area of Science:

• Neurology
• Artificial Intelligence
• Medical Imaging

Background:

• Alzheimer's disease (AD) is a leading cause of death, characterized by cognitive decline and memory loss.
• Current diagnostic methods for AD can be subjective and lack objectivity.
• Deep learning offers a promising approach for objective and automated analysis of medical images.

Purpose of the Study:

• To develop and evaluate an automated deep learning framework for accurate Alzheimer's disease classification using MRI images.
• To reduce bias and variability associated with traditional image preprocessing and hyperparameter optimization.

Main Methods:

• A novel framework, A3C-TL-GTO, combining transfer learning and Gorilla Troops optimization was proposed.
• The framework was evaluated on the Alzheimer's Dataset and the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset using MRI scans.
• The approach minimizes preprocessing steps and optimizes hyperparameters for enhanced classification performance.

Main Results:

• The A3C-TL-GTO framework achieved high accuracy in classifying Alzheimer's disease.
• Achieved 96.65% accuracy on the Alzheimer's Dataset and 96.25% accuracy on the ADNI dataset.
• Demonstrated superior performance compared to existing state-of-the-art methods.

Conclusions:

• The A3C-TL-GTO framework provides an accurate and objective tool for early Alzheimer's disease detection.
• The proposed method shows significant potential for improving patient care through early diagnosis.
• The framework's adaptability to other imaging modalities suggests broad applicability in medical diagnostics.