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: | Grant Haskins |
| Institution: | EvoAI (new start-up) |
| Department: | Machine Learning and Deep Learning |
| Country: | |
| Proposed Analysis: | We wish to develop a set of neural networks that can perform both bidirectional image synthesis (MRI to PET and PET to MRI). Additionally, we would like to develop a set of networks that perform regression of image analysis results both using the image that was used to generate those results and the corresponding image in a different modality. In the second instance, we would combine the first and second methods to create an end-to-end framework. Variants of the generative adversarial network (CycleGAN most likely) will be used for the MRI->PET and PET->MRI mapping. |
| Additional Investigators |
