Abstract :

Alzheimer’s Disease (AD) Is A Progressive Neurodegenerative Disorder That Requires Early And Accurate Diagnosis For Effective Clinical Management. Recent Deep Learning Approaches Using MRI Data Often Suffer From Overfitting And Reduced Generalization Due To Limited Training Samples And High Data Variability. To Address This Issue, This Work Presents An Extended Alzheimer’s Disease Classification Framework Using Landmark-guided Hippocampal MRI Slice Selection Combined With A Dropoutenhanced LeNet Convolutional Neural Network. The Inclusion Of A Dropout Layer Improves Model Robustness By Reducing Overfitting And Enhancing Generalization Performance. Experiments Conducted On The Publicly Available Alzheimer’s Disease Neuroimaging Initiative (ADNI) Dataset Demonstrate That The Proposed LeNet With Dropout Achieves Significantly Improved Classification Performance, Reaching Up To 100% Accuracy Across Selected Hippocampal Views. Furthermore, A Secure And User-friendly Flask-based Interface With Authentication Is Developed To Facilitate Real-time System Testing And Result Visualization. The Experimental Results Validate That The Proposed Extension Enhances Diagnostic Accuracy, Model Stability, And Practical Usability, Making It A Reliable Tool For Computer-aided Alzheimer’s Disease Diagnosis.

Published:

12-4-1-2026

Issue:

Vol. 26 No. 4-1 (2026)

Page Nos:

358 - 366

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite