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: | Rahmat Beheshti |
| Institution: | University of Delaware |
| Department: | Computer & Info Sciences - Epidemiology |
| Country: | |
| Proposed Analysis: | We would like to investigate multimodal data augmentation with the overarching aim of helping to address the scarcity of medical data for deep learning applications. Our current plan is to synthesize MRI images, which can be prohibitively expensive to collect in large quantities, from clinical data, which is more readily available, with deep learning models and to use such synthetic data to improve the performance of an available state-of-the-art model based on ADNI (yet to be determined). We aim to demonstrate how incorporating synthetic data into a model (by increasing the modalities that the model has access to) can improve its performance. We may also extend into other modalities (PET), either as inputs or outputs, depending on the results we observe during the development process. The quantity and breadth of the data from ADNI is a unique and important resource for this research. |
| Additional Investigators | |
| Investigator's Name: | Tyler Ballance |
| Proposed Analysis: | Tyler is a junior student who will directly work on the proposed analysis presented by the main investigator in this project. |
