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: | Mohammad Khaja Mushtaq |
| Institution: | USC |
| Department: | Computer Science |
| Country: | |
| Proposed Analysis: | “In collaboration with Dr. Ioannis Pappas from USC LONI, our goal is to create a model that will produce synthetic patient MRI data that mimic the properties of the original MRI data. We are going to do so by using the anatomical images (e.g., T1, T2, Flair) of the ADNI dataset to train neural network models that will be able to produce synthetic data. These models include (but are not limited to) auto-encoders, U-net models, and more. The goal of this project is to advance opportunities for data partners to share patient data without sharing the original data. At the same time, they can share a synthetic version of the data as it is derived from the neural network that is still usable for downstream analysis (e.g. volumetric analysis). We hope this model will foster collaborations and data sharing between data partners that prefer to keep their data untouched.” |
| Additional Investigators | |
| Investigator's Name: | Swaraj Vatsa |
| Proposed Analysis: | “In collaboration with Dr. Ioannis Pappas from USC LONI, our goal is to create a model that will produce synthetic patient MRI data that mimic the properties of the original MRI data. We are going to do so by using the anatomical images (e.g., T1, T2, Flair) of the ADNI dataset to train neural network models that will be able to produce synthetic data. These models include (but are not limited to) auto-encoders, U-net models, and more. The goal of this project is to advance opportunities for data partners to share patient data without sharing the original data. At the same time they can share a synthetic version of the data as it's derived from the neural network that is still usable for downstream analysis (e.g. volumetric analysis). We hope this model will foster collaborations and data sharing between data partners that prefer to keep their data untouched.” |
