Scholarlink

Different areas of the brain alter as a result of different kinds of brain disorders. Alzheimer's disease is a long-term condition that leads to memory loss due to the degeneration of brain cells. Forgetfulness and confusion are two of the most common cognitive mental health issues in Alzheimer's sufferers. Nowadays, image-based computer-aided diagnosis is being used more and more in the diagnosis of Alzheimer's disease. A VGG16-based model is suggested in this study to improve AD categorization. The original sources of the brain scans were internet databases like the AD Neuroimaging Initiative (ADNI). In order to reduce the dimensionality of the extracted features, the ReliefF technique is used to choose the active features from the retrieved feature values. ReliefF is a very effective method for handling real-time, noisy data. The Manhattan distance metric, which only requires a few features to accurately define the data, is used by the method. This methodology facilitates precise location selection to improve illness identification. The experimental findings demonstrate that the suggested technique outperformed the LSTM, NN, and Deep neural network models in illness prediction.

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 Identification and Classification Using the VGG16 Deep Convolutional Neural Network Model

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Riyam Patel,
  • Adesh Jothi Prasanna,
  • Borra Sivaiah,
  • Punyaban Patel,
  • Reddyvari Venkateswara Reddy,
  • Bibhudatta Sahoo

摘要

Different areas of the brain alter as a result of different kinds of brain disorders. Alzheimer's disease is a long-term condition that leads to memory loss due to the degeneration of brain cells. Forgetfulness and confusion are two of the most common cognitive mental health issues in Alzheimer's sufferers. Nowadays, image-based computer-aided diagnosis is being used more and more in the diagnosis of Alzheimer's disease. A VGG16-based model is suggested in this study to improve AD categorization. The original sources of the brain scans were internet databases like the AD Neuroimaging Initiative (ADNI). In order to reduce the dimensionality of the extracted features, the ReliefF technique is used to choose the active features from the retrieved feature values. ReliefF is a very effective method for handling real-time, noisy data. The Manhattan distance metric, which only requires a few features to accurately define the data, is used by the method. This methodology facilitates precise location selection to improve illness identification. The experimental findings demonstrate that the suggested technique outperformed the LSTM, NN, and Deep neural network models in illness prediction.