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: | wei ge |
| Institution: | SCUEC |
| Department: | The College of Biomedical Engineering |
| Country: | |
| Proposed Analysis: | According to the structural characteristics of channel domain attention mechanism, Alex net network and full convolution neural network, they are applied to the model to form a new network model: hierarchical FCN combined with channel attention mechanism. After data set registration, scalp and skull removal, bias field correction and other preprocessing, the sMRI image of the whole brain is sent to the network for training. The verification method is 50% cross verification, and finally the performance index of the network model is output. Because the brain images of AD and MCI are highly correlated, the method of transfer learning is adopted in the classification of SMCI vs pmci, that is, the parameters learned in AD vs NC network are applied to SMCI vs pmci without training from scratch. Then the effectiveness of transfer learning is verified by experiments |
| Additional Investigators |
