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: | Nicodemus Awarayi |
| Institution: | University of Energy and Natural Resources |
| Department: | Computer Science and Informatics |
| Country: | |
| Proposed Analysis: | The use of deep learning or machine learning in classifying Alzheimer Disease (AD) has been shown to be successful, however it is not conclusive because there are still certain problems. Many studies use ROI to extract traits, although all of them may be important. Deep learning solves this problem, but it is more sophisticated and requires more datasets. To train a robust classifier for illness identification in medical imaging, a substantial amount of data must be collected. Diagnostics have surely become more complex due to the diverse dimensions and composition of disease data, needing an adequate model choice to handle the issue. The structure of the data is ignored by most deep learning algorithms, despite the fact that it has been shown to boost classification performance in classical machine learning. Our research aims to address some of these issues by constructing a more effective deep learning model for classifying Alzheimer's disease at various stages. To preprocess the data, we will use a variety of rigorous data preprocessing approaches. We would build a data fusion technique that integrates MRI and PET images for our training, testing, and validation in order to enhance the size of our dataset. A variety of data augmentation techniques would be used as well. The CNN or the Capsule network will be used to create our deep learning model. |
| Additional Investigators |
