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: | Lan Yang |
| Institution: | Xi'an Jiaotong university |
| Department: | School of Mathematics and Statistics |
| Country: | |
| Proposed Analysis: | By considering the brain regions being the nodes and the FCs being the edges, the brain can be modeled as a graph. However, most graph dictionary learning methods are linear models that neglect the nonlinear higher-level representations contained in graph-structure data. Besides, some graph dictionary learning methods rely on the assumption that all the graph signals lie on the same weighted graph, which is very limited in practical application, especially for fMRI data where the weight matrix of the brain graph for each subject is distinct. To sum up, most existing dictionary learning methods either ignore the structure of brain graph topology, or fail to learn the nonlinear higher-level representation of data, or are unable to process the graph signals in different graphs. To address these problems, we aim to propose a graph deep dictionary learning method to identify the neural markers related to Alzheimer disease. |
| Additional Investigators |
