Improved Alzheimer's Disease Detection Using an Adaptive Spatial Attention-Based Twin Neural Network

Alzheimer’s disease (AD) is one of the most prevalent forms of dementia, typically initiating with mild memory loss and progressively leading to severe cognitive decline. Early diagnosis is critical for effective intervention and improving patient outcomes. However, existing diagnostic approaches face challenges such as long prediction times, limited feature extraction capability, and the requirement for extensive training data, particularly in Machine Learning (ML)-based systems. To address these issues, this study proposes a novel computer-aided diagnostic framework called Adaptive Spatial Attention-based Twin Neural Network (ASTNet) for early AD detection using MRI data. Unlike traditional methods, ASTNet integrates several components: a biased fuzzy clustering-based segmentation technique that enhances tissue segmentation by emphasizing brain-relevant regions while suppressing skull and irrelevant tissues; Possibilistic C-Means (PCM) to improve segmentation robustness; a Convolutional Bidirectional LSTM (CBi-LSTM) network for context-aware feature extraction that captures temporal dependencies and reduces high-dimensional noise; and an adaptive spatial attention-based Twin Neural Network (TNN) for disease classification that improves spatial feature discrimination across cognitively normal (CN), mild cognitive impairment (MCI), and AD categories. The proposed approach was evaluated on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset and achieved a classification accuracy of 0.9909, outperforming the compared Deep Learning (DL) models. Furthermore, the model demonstrates computational efficiency under the evaluated experimental setting and shows potential for computer-aided clinical decision support.