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: | An Vo |
| Institution: | Feinstein Institutes for Medical Research |
| Department: | Center for Neurosciences |
| Country: | |
| Proposed Analysis: | Our goal is to use deep learning neural network to extract intrinsic AD network biomarkers (ADDLN) from structural (MRI) and functional imaging data (amyloid PET and FDG-PET) that are unbiased regarding subject variability and instrumentation. After training the network to correlate with disease severity ratings and cognitive assessments, we will compute deep learning-based prediction scores for each subject and time point as measures of progression at the individual scan level. For natural history, we will assess ADDLN progression in longitudinal scans from AD subjects scanned at baseline, 3 months, 6 months, 12 months, 18 months, 24 months, 36 months, and 48 months as part of ADNI. |
| Additional Investigators | |
| Investigator's Name: | Nha Nguyen |
| Proposed Analysis: | Design neural network architecture: We will use CNN to predict disease severity ratings or cognitive performance measures. For training, the inputs will be 3D images and either disease severity ratings or cognitive performance measures. Outputs will be the prediction scores for the respective clinical descriptors in the testing samples. |
