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: | Rongqin Chen |
| Institution: | Shenzhen Institute of Advanced Technology,Chinese Academy of Sciences |
| Department: | Institute of Advanced Computing and Digital Engine |
| Country: | |
| Proposed Analysis: | Our team is committed to the direct and indirect structure-function causal influence in brain, in order to detect Alzheimer’s Disease (AD) at the earliest possible stage and identify ways to track the disease’s progression with biomarkers. White matter tracks reconstructed from DTI provide a foundation for structural connectivity (SC) and can be used to quantify the (static) anatomical connection strength between brain regions. On the other hand fMRI enables us to map out dynamic neural activity distributions across the brain, whereas the coherence of fluctuations is usually referred to as functional connectivity (FC). Alterations of such functional state are mainly related to the natural development of the brain, aging or disease. Intuitively one might follow then the motto “structure determines function”, but it has been shown that the relationship between brain structure and function is quite complex and still a focus of intense research. For instance, brain regions with robust SC usually show also high FC, but the inverse is not necessarily true. While FC is a statistical measure with no information concerning the directionality of the relation, effective connectivity and directed functional connectivity measures try to infer direct and indirect causal dependencies in functional imaging data. Thus connectivity measures derived from different modalities can provide distinct, but complementary aspects of brain connectivity, as well as it will help us to discover biomarkers for tracking disease progression, and realizing the early detection of AD. We will adopt a graph neural network (GNN) framework to infer the direct and indirect causal dependencies of functions based on the structural anatomical layout. A GNN allows us to process graph‐structured spatio‐temporal signals, providing a possibility to combine structural information with temporal neural activity profiles. By combining fMRI with DTI data, the idea is to replicate brain dynamics more accurately, to get an improved understanding of functional interactions between brain regions, which are physically constrained by their structural backbone. Accordingly this approach appears to be promising for the understanding which brain regions are related to AD. |
| Additional Investigators |
