Attention Gated-VGG with deep learning-based features for Alzheimer's disease classification.

Journal: Neurodegenerative disease management
Published Date: Sep 10, 2025

Abstract

BACKGROUND: Alzheimer's disease (AD) is considered to be one of the neurodegenerative diseases with possible cognitive deficits related to dementia in human subjects. High priority should be put on efforts aimed at early detection of AD. RESEARCH DESIGN AND METHODS: Here, images undergo a pre-processing phase that integrates image resizing and the application of median filters. After that, processed images are subjected to data augmentation procedures. Feature extraction from WOA-based ResNet, together with extracted convolutional neural network (CNN) features from pre-processed images, is used to train proposed DL model to classify AD. The process is executed using the proposed Attention Gated-VGG model. RESULTS: The proposed method outperformed normal methodologies when tested and achieved an accuracy of 96.7%, sensitivity of 97.8%, and specificity of 96.3%. CONCLUSION: The results have proven that Attention Gated-VGG model is a very promising technique for classifying AD.

Authors

  • Deepthi K Moorthy
    Department of Computer Science and Engineering, Kalasalingam Academy of Research and Education, Srivilliputhur, Tamil Nadu, India.
  • P Nagaraj
    Department of Computer Science and Engineering, Kalasalingam Academy of Research and Education, Krishnankoil, Srivilliputhur, Tamil Nadu, India. Electronic address: [email protected].

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals