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: | Vaishnav Srinidhi |
Institution: | Vellore Institute of Technology, Vellore |
Department: | School of Computer Science and Engineering |
Country: | |
Proposed Analysis: | We request access to this dataset to enable us to work on a state of the art Computer Aided Diagnostic(CAD) problem and build a neural network architecture to predict the diagnosis of Alzheimer's Disease (AD). Using biomarkers present in the dataset, we plan on training a model based on the transfer learning concept. Using transfer learning, we will identify the best model for disease diagnosis by comparing with state of the art ImageNets. The most important biomarkers (attributes) will be learned so that we can accurately predict the likelihood that a patient is suffering from AD. We also wish to experiment whether the privacy preserving technique of Federated Learning lends any merit to the medical data domain. Such research is lacking and these results would benefit the scientific and medical community. The ADNI dataset is the most comprehensive one of its kind, and using this data would allow for a valid extrapolation of theory to real life scenarios. |
Additional Investigators |