Alzheimer's Disease Detection using CDTN over 3-D CNN

Abstract

Alzheimer’s Disease (AD) is a neurodegenerative disorder that progressively impairs cognitive function, making early detection essential for effective management. With the advancements in artificial intelligence, deep learning models have emerged as powerful tools for analysing MRI scans to aid in AD diagnosis. This paper compares two distinct AI models: the Conditional Deep Triplet Network (CDTN) based on VGG16 and the 3D Convolutional Neural Network (3D CNN). While CDTN employs deep metric learning to refine classification accuracy and achieves 95% accuracy, the 3D CNN model, which leverages volumetric feature extraction, reports an accuracy of 89%. This comparative study evaluates their architectural differences, performance metrics, and practical usability in clinical applications. By analysing these models, we aim to provide a clearer understanding of their strengths and limitations, offering insights into how AI can contribute to more reliable and efficient AD detection.