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: | Stiven Roytman |
| Institution: | University of Michigan |
| Department: | Radiology |
| Country: | |
| Proposed Analysis: | We were able to get a proof-of-concept variational auto-encoder neural network model working with our in-house PET dataset, to predict clinical outcomes from latent space variables, and then decode the relevant entries on the latent vector into an interpretable, synthetic PET image showing the features that the model used for prediction. We would like to replicate the model with a big publicly available dataset for the publication so that we may publish the model weights and have other researchers be able to use the pre-trained model to answer their own questions. We will also use our in-house dataset as a test sample for model generalizability. |
| Additional Investigators | |
| Investigator's Name: | Prabesh Kanel |
| Proposed Analysis: | Same as previously detailed - Dr.Kanel will be a senior author and supervisor on this work. |
| Investigator's Name: | August VanHout |
| Proposed Analysis: | Same as previously detailed - Dr.Kanel will be a senior author and supervisor on this work. |
