Scholarlink

Alzheimer’s disease (AD) affects million people worldwide, marked by progressive neurodegeneration leading to cognitive decline. Early detection is critical for effective treatment and disease management, yet it remains challenging due to the intricate nature of medical imaging. This study introduces an enhanced Densely Connected Convolutional Network (DenseNet-121) to detect stages of AD. Utilizing datasets associated with AD, the model was trained over 50 epochs with a batch size of 32, achieving an accuracy of 95%. These results highlight the model’s potential for clinical integration, improving early diagnostic capabilities and advancing our understanding of AD progression.

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

Alzheimer’s Disease Diagnosis with Enhanced Densely Connected Convolutional Networks

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Hai T. Nguyen,
  • Huong H. Luong,
  • Le Q. Hung,
  • Nam D. L. Tran

摘要

Alzheimer’s disease (AD) affects million people worldwide, marked by progressive neurodegeneration leading to cognitive decline. Early detection is critical for effective treatment and disease management, yet it remains challenging due to the intricate nature of medical imaging. This study introduces an enhanced Densely Connected Convolutional Network (DenseNet-121) to detect stages of AD. Utilizing datasets associated with AD, the model was trained over 50 epochs with a batch size of 32, achieving an accuracy of 95%. These results highlight the model’s potential for clinical integration, improving early diagnostic capabilities and advancing our understanding of AD progression.