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: | Ricardo Bigolin Lanfredi |
| Institution: | University of Utah |
| Department: | Electrical and Computer Engineering |
| Country: | |
| Proposed Analysis: | We are developing a model for dataset visual explanation, trying to find what would change, for one specific subject, from an MRI volume with a certain severity of a disease to one with another severity, using an adversarial training setup. This is similar to what is done by Baumgartner et al in Visual Feature Attribution using Wasserstein GANs (https://arxiv.org/abs/1711.08998), but using regression labels (MMSE or other) instead of classification labels. We would like to have access to the dataset to be able to compare our model with their results, and maybe be able to visualize different kinds of disease progression in different levels of MMSE. |
| Additional Investigators |
