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: | Lin Tang |
Institution: | Yunnan University |
Department: | Statistics |
Country: | |
Proposed Analysis: | We consider automatic classification of cognitively normal, mild cognitive impairment and Alzheimer's disease using the hippocampus surface data. To this end, we will use a multiclass functional logistic regression model to characterize the relationship between the class label of each subject and a set of functional and scalar predictors. Given the 3D MRI scans of the cognitively normal, MCI and AD subjects, we consider using the FIRST method to segment the hippocampus substructures, and hippocampus surfaces can be automatically reconstructed by the marching cube method. Then we consider using the topology optimization method to introduce two cuts on hippocampal surface to convert it into genus zero surface with two open boundaries. The feature image of the surface can be computed by combining the conformal factor and mean curvature and linearly scaling the dynamic range into [0,255]. Next, we consider using an inverse consistent fluid registration algorithm to register the feature image of each surface in the dataset to a common template. Finally, we can calculate the hippocampus radial distance, which will be used as the functional predictors in the proposed model. For the scalar covariates in the model, we consider the demographic information such as the gender, marital status, handedness, education length and so on. The estimation methods of the proposed model will be systematically investigated. |
Additional Investigators |