Alzheimer's disease Recognition Classification Study Using MRI Images Based on Deep Learning and Dual Multilayer Attention Mechanisms

Introduction: Current deep learning-based computer-aided diagnosis (CAD) techniques face challenges in hierarchical feature extraction and computational efficiency. Traditional convolutional neural networks (CNN) often focus on local or single-scale information, neglecting global correlations of brain atrophy and multiscale pathological features. Additionally, the parameter explosion problem in deep networks limits model's generalization ability on small and medium-sized datasets. While the introduction of attention mechanisms has significantly improved feature extraction and enhanced CNN recognition capabilities, existing attention mechanisms are mostly single-scale, focusing on feature maps at specific hierarchical levels and ignoring the correlations between features of different layers.Material and Methods: To address these issues, this study proposes a lightweight model combining a shallow feature pyramid CNN with a Dual Multi-level Attention (DMA) mechanism. Experiments using the public OASIS-۱ dataset, which contains ۸۶,۴۳۷ MRI images across ۴ categories, employ a focal loss function to handle class imbalance.Results: The results show that the model including DMA outperforms both the baseline CNN and the single-scale attention mechanism in terms of accuracy (ACC), sensitivity (SEN), and specificity (SPE). Specifically, compared to CNN and CNN+CBAM: ACC improved by ۳.۳۳% and ۱.۲۶%, SEN improved by ۱۳.۲% and ۰.۹%, and SPE improved by ۱%.Conclusion: The model demonstrates significant advantages in distinguishing small-sample classes and differentiating between very mild dementia and normal controls, highlighting its superiority in fine-grained pathological discrimination.

کلیدواژه ها:

Alzheimer's disease ، Deep learning ، Artificial intelligence ، magnetic resonance imaging ، classification