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: | Annemieke ter Telgte |
| Institution: | VASCage GmbH |
| Department: | VASCage GmbH |
| Country: | |
| Proposed Analysis: | Small acute brain infarcts can be detected as focal hyperintense lesions on the diffusion-weighted imaging (DWI) scan and are also termed DWI lesions. The prevalence of DWI lesions increases with age and severity of MRI markers of cerebral small vessel disease (SVD) and first data suggest that cases with a DWI lesion are at increased risk of poor clinical outcome. However, much is still unknown about the epidemiology of DWI lesions. As these lesions are usually asymptomatic and only detectable on the DWI scan for a short period (mostly up to 2-4 weeks after infarct onset), large datasets are required to provide reliable estimates on risk factors of DWI lesions and their prognosis. In order to obtain such large datasets, tools that automatically detect DWI lesions are essential. In this project, we aim to use ADNI data to develop a tool based on deep learning for the automated detection of DWI lesions. |
| Additional Investigators | |
| Investigator's Name: | Nadja Gruber |
| Proposed Analysis: | Small acute brain infarcts can be detected as focal hyperintense lesions on the diffusion-weighted imaging (DWI) scan and are also termed DWI lesions. The prevalence of DWI lesions increases with age and severity of MRI markers of cerebral small vessel disease (SVD) and first data suggest that cases with a DWI lesion are at increased risk of poor clinical outcome. However, much is still unknown about the epidemiology of DWI lesions. As these lesions are usually asymptomatic and only detectable on the DWI scan for a short period (mostly up to 2-4 weeks after infarct onset), large datasets are required to provide reliable estimates on risk factors of DWI lesions and their prognosis. In order to obtain such large datasets, tools that automatically detect DWI lesions are essential. In this project, we aim to use ADNI data to develop a tool based on deep learning for the automated detection of DWI lesions. |
