There are many active research projects accessing and applying shared ADNI data. Use the search above to find specific research focuses on the active ADNI investigations. This information is requested annually as a requirement for data access.
| Principal Investigator | |
| Principal Investigator's Name: | Qianyun Chen |
| Institution: | The Chinese University of Hong Kong |
| Department: | Imaging and Interventional Radiology |
| Country: | |
| Proposed Analysis: | Detection and prediction of MCI due to AD based on diffusion MRI with deep learning Background: Most deep learning studies work on mild cognitive impairment (MCI) detection from AD and normal and conversion prediction based on structural MRI and PET imaging, but the performance on using diffusion imaging to detect and predict MCI progression is still under exploration. Purpose: The study will aim at exploring the utilities of deep learning in detecting and predicting MCI based on diffusion MRI. Method: We plan to select T1 and diffusion MR images of ~200 subjects for each group (AD, MCI and HC), with 90% of data for training and the rest 10% for testing. Convolutional neural network will be adopted to pre-train with AD and HC data, and then trained with MCI data to extract image feature. The trained network will be tested with testing set and the performance will be evaluated by metrics such as accuracy, sensitivity and specificity. |
| Additional Investigators |
