CE-AH: A contrast-enhanced attention hierarchical network for Alzheimer's disease diagnosis based on structural MRI

Tianxiang Wang, Qun Dai, Han Lu

Abstract: Numerous deep learning-based methods utilizing structural magnetic resonance imaging (sMRI) have been developed for diagnosing Alzheimer's disease (AD). However, the majority of these methods overlook the localized nature of brain atrophy. Moreover, they often rely on a single scale, neglecting the global structural information. To address these issues concurrently, this study introduces a Contrast-Enhanced Attention Hierarchical (CE-AH) network for AD diagnosis. Initially, we employ pretraining through contrastive learning to bolster the network's feature extraction capabilities. Subsequently, we engineer a hierarchical model that integrates dual attention mechanisms to extract multi-scale discriminative features. To overcome the convergence challenges and training instability inherent in patch-based methods, we implement group normalization in place of batch normalization. The CE-AH model's performance is assessed on the ADNI dataset, yielding outstanding classification outcomes. Furthermore, experimental results indicate that the training process of our proposed model is remarkably stable.