This take a look at affords an evaluation of three-dimensional (3-d) magnetic resonance imaging (MRI) statistics with the goal of diagnosing neurodegenerative sicknesses. A Convolutional Neural network (CNN) model was utilized to extract quantitative capabilities from three-D MRI facts to be expecting the presence and/or severity of these conditions. The extracted functions have been used to classify sufferers into healthful, CNN model achieved a sensitivity of ninety seven.43%, 1.27% specificity, and an AUC of 0.ninety four. The approach is likewise shown to be sturdy in phrases of variance over distinctive hyperparameter values. The have a look at offers insights into growing 3-D MRI-based totally early prognosis and detection of neurodegenerative sicknesses and may be similarly investigated with larger datasets for extra accurate outcomes.

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

An Analysis of 3D Magnetic Resonance Imaging Data for Diagnosing Neurodegenerative Diseases

  • Ananta Ojha,
  • Dhananjay Kumar Yadav,
  • Neeraj Sharma,
  • Salahuddin

摘要

This take a look at affords an evaluation of three-dimensional (3-d) magnetic resonance imaging (MRI) statistics with the goal of diagnosing neurodegenerative sicknesses. A Convolutional Neural network (CNN) model was utilized to extract quantitative capabilities from three-D MRI facts to be expecting the presence and/or severity of these conditions. The extracted functions have been used to classify sufferers into healthful, CNN model achieved a sensitivity of ninety seven.43%, 1.27% specificity, and an AUC of 0.ninety four. The approach is likewise shown to be sturdy in phrases of variance over distinctive hyperparameter values. The have a look at offers insights into growing 3-D MRI-based totally early prognosis and detection of neurodegenerative sicknesses and may be similarly investigated with larger datasets for extra accurate outcomes.