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: | Suprosanna Shit |
Institution: | TUM |
Department: | Informatics |
Country: | |
Proposed Analysis: | In many medical applications, high-resolution images are required to facilitate early and accurate diagnosis. However, due to economical, technological or physical limitations, it may not be easy to obtain images at the desired resolution. Super-resolution techniques solve this problem by creating a High Resolution (HR) image from a Low-Resolution one (LR). In the past decade, a variety of super-resolution methods have been successfully applied to imaging data to increase the spatial resolution of scans after the acquisition has been performed. However, these approaches have been proposed for 2D data. In this project we aim to develop an architecture for MRI super-resolution that completely exploits the available volumetric information contained in MRI scans, using 3D convolutions to process the volumes and taking advantage of an adversarial framework, improving the realism of the generated volumes. |
Additional Investigators |