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: | Ludvig Renbo Olsen |
| Institution: | Aarhus University |
| Department: | Department of Cognitive Science |
| Country: | |
| Proposed Analysis: | Master's thesis: Applying federated deep learning to medical imaging for detection of Alzheimer's disease. Federated learning allows training of machine learning models on sensitive data without data sharing by performing the training at the client (data provider) without transferring the data. It would, for instance, be possible to train an artificial neural network on data from multiple hospitals without the data leaving the hospital servers. In this project, I wish to examine the application of federated deep learning to medical imaging data (e.g. MRI). Alzheimer's Disease is an important field of research and the structure of the datasets (multi-center, multi-scanner, large) makes it a good case. The initial investigation will be to compare a centrally/conventionally trained deep neural network binary classifier (AD vs. control) to the same network trained in a simulated federated learning setting. Experiences from this research could add an additional tool/framework to the collaboration opportunity space in AD research. |
| Additional Investigators |
