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: | Hyo Min Kim |
| Institution: | Korea Advanced Institute of Science and Technology |
| Department: | Bio and Brain Engineering |
| Country: | |
| Proposed Analysis: | Utilize this dataset to extract the graph representation of fMRI data and uses a graph neural network to predict the severity of Alzheimer's disease based on both the fMRI data and demographic features. The proposed steps are as follows: 1. Canonical preprocessing: slice timing correction, motion correction, spatial normalization to a common brain space, and brain parcellation to divide the brain into different regions of interest (ROIs) using a predefined atlas such as the Automated Anatomical Labeling (AAL) atlas or the Human Connectome Project (HCP) atlas. 2. Extract graph Representation: Construct a functional connectivity matrix by computing the Pearson correlation coefficient between the mean time series of each pair of ROIs. Use the resulting matrix to construct a weighted undirected graph where nodes correspond to ROIs, and edges represent the strength of functional connectivity between them. 3. Graph Neural Network: Use a graph neural network (GNN) to learn the relationship between the fMRI data and demographic information and predict the severity of Alzheimer's disease. The GNN takes the graph representation of the fMRI data and demographic features as input and learns a representation of each node that captures its connectivity pattern with other nodes. |
| Additional Investigators |
