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: | Hugo Kuijf |
| Institution: | UMC Utrecht |
| Department: | Image Sciences Institute |
| Country: | |
| Proposed Analysis: | Neuropathology studies have established cerebral cortical microinfarcts (CMIs) as a very common form of cerebrovascular damage and a likely contributor to dementia. While long considered "invisible" in vivo, it has become clear that CMIs can be visualized on high-resolution neuroimaging protocols used in research and clinical routine worldwide (i.e. 3D T1-weighted 3T MRI). To unleash the full potential of this novel biomarker, leveraging on the wealth of data from already collected cohorts around the world, challenges in detection and quantification of CMIs on MRI must be overcome. In particular, CMI detection currently depends on visual rating, which is time-consuming with limited sensitivity. Our automatic machine learning based neuroimaging-analysis tool for CMI detection reduces rating time and improves sensitivity. In this project, we will further establish our machine learning based CMI detection tool by implementing transfer learning methodology to deploy this tool on scans from multiple vendors. Using existing longitudinal cohorts (including ADNI), we will subsequently validate CMIs as a biomarker for vascular contributions to neurodegenerative diseases, relevant to prognosis (i.e. cognitive decline), with an aetiological signature that is different from existing markers of vascular brain injury. This project will thus validate CMIs as a novel biomarker and potential target for future therapeutic approaches. Data resulting from this project will be provided to ADNI (i.e. the location of identified CMIs). |
| Additional Investigators |
