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: | Yuan yang Deng |
Institution: | Tsinghua University |
Department: | biomedical engineering |
Country: | |
Proposed Analysis: | Accurate diagnosis of mild cognitive impairment (MCI) is important for early treatment and delayed progression of Alzheimer's disease. However, there is still a lack of reliable auxiliary diagnosis techniques because of the mild symptoms in the MCI stage. The individual morphological brain network based on structural magnetic resonance imaging provides an effective way to sensitively capture such subtle changes in MCI. In this project, we will utilize the superiority of geometric deep learning technology on manifold and graph to develop a reliable individual morphological brain network construction method, and apply it to the study of MCI disease. For the methodology study, we first propose a deep cortical surface parcellation network that could directly work on the original brain surfaces. Then we establish a joint learning method for brain network structure and similarity metric, which can optimize brain network structure adaptively and improve the accuracy of similarity learning. For the application research, we utilized the established method to reveal the abnormal brain network topology in MCI and make an accurate diagnosis of MCI. This project would offer new techniques for network neuroscience, and provide technical supports for the medical study of MCI disease. |
Additional Investigators |