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: | Raima Adhikary |
| Institution: | Jahangirnagar University |
| Department: | Institute Of Information Technology |
| Country: | |
| Proposed Analysis: | Early detection of Alzheimer's disease (AD) has been in research areas for decades due to Alzheimer's being the most dangerous form of dementia. The classification of stages of Alzheimer's disease has been a common problem for neurological and clinical branch to discover its solution. Since there is no cure for this disease, the earliest detection of AD is one of the most important tasks. At medical field, the data collection is limited due to financial and privacy issues. Thus, the very limited information extracted from various diagnostic tools play a vital part in research. With this limitation in mind, this research work aims to extract information from singular modality as much as possible and apply residual network in order to classify between the multiple stages of Alzheimer’s Disease. A pre-trained residual network of high capacity with skip connection and simple SVM is applied as image classification technique for the pre-processed brain Magnetic Resonance images (MRI). For the imaging data, data augmentation has been performed before feeding them to the network. In order to make a subset based on hippocampus changes, ROI mask mapping is added as hippocampal region extractor from coronal view images. In order to obtain useful features from imaging modality, area of hippocampus regions obtained from 2d images are to be compared with each other. Furthermore, comprehensive analysis between coronal and axial views is to be performed to distinguish in which case atrophy volume can be detected more correctly. |
| Additional Investigators |
