Scholarlink

Alzheimer’s disease (AD), a leading cause of dementia worldwide, primarily affects individuals over the age of 60. Early diagnosis is critical to slowing disease progression and preventing brain damage. In this paper, we propose a hybrid Deep Learning (DL) model combining Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks to classify Magnetic Resonance Imaging (MRI) images into four stages of Alzheimer’s disease. Our optimized architecture utilizes an extensive data augmentation method through TensorFlow’s ImageDataGenerator to increase data variability, reduce overfitting, and improve generalization to new data. Our model outperforms existing state-of-the-art methods, achieving an accuracy of 99.38%, which demonstrates the robustness of this architecture in AD detection.

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

Optimized Hybrid Deep Learning Model for Accurate Classification of Alzheimer’s Stages

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Maysam Chaari,
  • Yassine Ben Ayed

摘要

Alzheimer’s disease (AD), a leading cause of dementia worldwide, primarily affects individuals over the age of 60. Early diagnosis is critical to slowing disease progression and preventing brain damage. In this paper, we propose a hybrid Deep Learning (DL) model combining Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks to classify Magnetic Resonance Imaging (MRI) images into four stages of Alzheimer’s disease. Our optimized architecture utilizes an extensive data augmentation method through TensorFlow’s ImageDataGenerator to increase data variability, reduce overfitting, and improve generalization to new data. Our model outperforms existing state-of-the-art methods, achieving an accuracy of 99.38%, which demonstrates the robustness of this architecture in AD detection.