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: | Muhammad Umar Khan |
| Institution: | University of Engineering and Technology Taxila |
| Department: | Electronics Engineering Department |
| Country: | |
| Proposed Analysis: | Although machine learning and deep learning techniques have significantly improved medical imaging systems for Alzheimer’s disease (AD) by providing diagnostic performance close to the human level. But the main problem faced during multi-class classification is the presence of highly correlated features in the brain structure. Here we propose a smart and accurate way of diagnosing AD based on the fusion of a novel Adaptive Local Cepstrogram Quadrant Patterns (ALCQP) features with DarkNet-19 features using an imbalanced three-dimensional MRI dataset. Experiments will be performed on Alzheimer's Disease Neuroimaging Initiative (ADNI) magnetic resonance imaging (MRI) dataset to confirm the superiority of the proposed model in terms of accuracy, efficiency, and robustness. To reduce the complexity (time and space) of the proposed system, the features will be reduced using a novel hybrid feature selection and reduction (HFSR) scheme. The model would be used to classify MRI into three categories: AD, mild cognitive impairment, and normal control. The proposed model will definitely exhibit noticeable improvement in accuracy as compared to the state-of-the-art methods. |
| Additional Investigators |
