DNCP: A Robust Artificial Intelligence Based Alzheimer's Disease Detection Methodology by Using Deep Neural Classification Principle

Alzheimer's disease (AD) is a neurodegenerative disorder that causes cognitive decline, memory loss, and ultimately death. Early and accurate detection of AD is crucial for timely intervention and improving patient outcomes. This study proposes DNCP: a robust deep learning (DL) based classification methodology for AD detection. The model integrates advanced preprocessing techniques, such as image registration, intensity normalization, and noise reduction, to enhance the quality of neuroimaging data. A multimodal learning approach is utilized to combine features from specific brain regions of interest (ROI), including the hippocampus, gray matter, and white matter. Comparative analysis was conducted against state-of-the-art models such as CNNs (ResNet, VGG-16, AlexNet), RNNs, and AutoEncoders, demonstrating the superior performance of DNCP. The proposed model achieved an accuracy of 95.7<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">%</sup>, sensitivity of 94.1%, and specificity of 96.2%, outperforming all other models. The results show that the DNCP model provides an efficient and reliable solution for early-stage Alzheimer's detection, opening doors for enhanced diagnostic tools in clinical settings.