ADNI data is made available to researchers around the world. As such, there are many active research projects accessing and applying the shared ADNI data. To further encourage Alzheimer’s disease research collaboration, and to help prevent duplicate efforts, the list below shows the specific research focus of the active ADNI investigations. This information is requested annually as a requirement for data access.
| Principal Investigator | |
| Principal Investigator's Name: | Jundong Liu |
| Institution: | Ohio University |
| Department: | Electrical Engineering and Computer Science |
| Country: | |
| Proposed Analysis: | We have been developing a shape-based biomarker identification framework for AD/MCI/NC, and the system performance is encouraging based on a small amount of data obtained from sanders-brown center on aging at University of Kentucky. In the project, we plan to further develop the framework to differentiate earliest stages of AD using cross-sectional and longitudinal data. A novel distance metric, based on the meridians of 3D shapes, will be used to measure the similarity/dissimilarity among extracted cortical and subcortical structures in MR images. Aim 1: identifies cross-sectional shape biomarker(s) for AD/MCI/NC based on subcortical and limbic structures using ADNI data sets. The discriminative capability of subcortical structures is characterized using a meridian-based shape representation and clustering framework, emphasizing the earliest changes. Aim 2: identifies longitudinal brain change patterns in AD based on spectral analysis techniques. Shape changes, in both cortical and subcortical areas, will be used to model longitudinal development in a manifold learning framework, and the estimated alternation pattern will be identified as a potential biomarker for early AD. Estimated deformation fields will be used to generate dissimilarities among different subjects. Aim 3: examines the effects of integrating subcortical and cortical structures, together with related non-image information, into a well-grounded feature selection and combination discrimination strategy. |
| Additional Investigators |