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: | Erin Liu |
| Institution: | Nanjing University of Posts and Telecommunications |
| Department: | Computer and Science |
| Country: | |
| Proposed Analysis: | We propose a deep latent representation collaborated sequence learning framework for AD progression modeling based on incomplete variable-length longitudinal multi-modal data. The proposed framework first exploits the complementary information between different modalities and learns comprehensive representations in the multi-modality fusion module. Then the learned representations are concatenated with cognitive scores and fed into RNN based sequence learning module, which encodes the temporal information within variable-length longitudinal input and models future AD progression by predicting cognitive score trajectories at an unlimited number of future time points. We employ the ”Model Filling” strategy in the sequence learning module to impute the missing data in longitudinal input and train the multimodality fusion module and the sequence learning module collaboratively to promote the learning of representations and network parameters. Experimental results need to be conducted on Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset validate the superiority of our method. |
| Additional Investigators |
