Scholarlink

In this study, we propose an improved selective cross-shaped window self-attention mechanism, incorporated into a depthwise separable CNN, that guides self-attention to attend only to the most relevant regions associated with Alzheimer’s disease and the relevant long dependencies and relationships between these affected regions. This new method was enhanced by multi-modal Conditional Progressive GAN. Our proposed method not only enhances the feature extraction efficiency but also maintains computational effectiveness. The results underscore the key role of advanced generative models in developing advanced deep learning methods for early Alzheimer’s detection. We evaluated our proposed method on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset, achieving a high accuracy of 99%.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Efficient Attention-Guided CNN for Alzheimer’s Disease Prediction

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Rahma Kadri,
  • Bassem Bouaziz,
  • Mohamed Tmar,
  • Faiez Gargouri

摘要

In this study, we propose an improved selective cross-shaped window self-attention mechanism, incorporated into a depthwise separable CNN, that guides self-attention to attend only to the most relevant regions associated with Alzheimer’s disease and the relevant long dependencies and relationships between these affected regions. This new method was enhanced by multi-modal Conditional Progressive GAN. Our proposed method not only enhances the feature extraction efficiency but also maintains computational effectiveness. The results underscore the key role of advanced generative models in developing advanced deep learning methods for early Alzheimer’s detection. We evaluated our proposed method on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset, achieving a high accuracy of 99%.