Scholarlink

The most prevalent type of dementia, Alzheimer’s disease (AD) progressively deteriorates cognitive function. Conventional diagnostic techniques for Alzheimer’s disease include obtaining previous medical records, doing MRI scans, and carrying out neuro-physical testing. For patients, though, these procedures can be troublesome, inconvenient and time consuming. This project uses a deep learning model called DenseNet121 to provide a revolutionary way for diagnosis of Alzheimer’s under Sustainable Development Goals (SDG-3) Good Health and Well-Being. Using classified Magnetic Resonance Imaging (MRI) data, encompassing extremely mild, mild, moderate, and non-demented phases of Alzheimer’s disease, the model will be trained and evaluated. The DenseNet121 model successfully collects characteristics from the MRI data by utilizing deep learning approaches, yielding encouraging outcomes. A Flask web application will be developed in this study that will offer a practical tool for healthcare professionals to utilize DL algorithms for disease diagnosis in a user-friendly manner. Potential management and treatment of AD depend heavily on early discovery. Through the integration of medical imaging data, this research highlights the potential of DL in facilitating early identification of AD.

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

Early Diagnosis of Alzheimer’s Disease Using Deep Learning

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Sanya Rastogi,
  • Malika Taneja,
  • R. Anto Arockia Rosaline,
  • G. Usha

摘要

The most prevalent type of dementia, Alzheimer’s disease (AD) progressively deteriorates cognitive function. Conventional diagnostic techniques for Alzheimer’s disease include obtaining previous medical records, doing MRI scans, and carrying out neuro-physical testing. For patients, though, these procedures can be troublesome, inconvenient and time consuming. This project uses a deep learning model called DenseNet121 to provide a revolutionary way for diagnosis of Alzheimer’s under Sustainable Development Goals (SDG-3) Good Health and Well-Being. Using classified Magnetic Resonance Imaging (MRI) data, encompassing extremely mild, mild, moderate, and non-demented phases of Alzheimer’s disease, the model will be trained and evaluated. The DenseNet121 model successfully collects characteristics from the MRI data by utilizing deep learning approaches, yielding encouraging outcomes. A Flask web application will be developed in this study that will offer a practical tool for healthcare professionals to utilize DL algorithms for disease diagnosis in a user-friendly manner. Potential management and treatment of AD depend heavily on early discovery. Through the integration of medical imaging data, this research highlights the potential of DL in facilitating early identification of AD.