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: | Aayush Jadhav |
Institution: | Liverpool John Moores University |
Department: | Computer Science |
Country: | |
Proposed Analysis: | Alzheimer's disease is the most prevalent form of dementia, which progresses with moderate memory loss and may result in the inability to hold a conversation. Alzheimer's disease affects regions of the brain responsible for thought, memory, and language. The primary objective of this research is to create a framework that employs Deep Learning and Image Segmentation-like watershed algorithm to target the regions of the brain that specifically regulate thought, memory, and language. A framework capable of detecting deterioration in the entorhinal cortex and hippocampus could classify Mild Cognitive Impairment (MCI), while deterioration in the cerebral cortex could classify Alzheimer's disease. (AD). This study can enhance patient outcomes as well as cut costs and time. During my studies, I identified a few research voids that I would like to fill with my current proposed framework. These are listed below: 1) Numerous frameworks extensively rely on Convolutional Neural Networks (CNNs) but fail to recognize the potential of Vision Transformers (ViTs). ViTs are relatively new to the field of image learning and outperform CNNs nearly fourfold in terms of computational accuracy and efficiency. 2) Many prior frameworks neglected to account for a layer that would incorporate demographic data in order to identify probable MCI or AD patients. This is crucial because depression, nutritional deficiencies, emotional distress, and medication complications may be misclassified as AD or MCI. 3) Classification frameworks that incorporate MRI images of the brain Cognitive Normal (CN) versus MCI versus AD typically do not use image processing techniques such as watershed segmentation, image segmentation, thresholding, and data manipulation techniques such as image augmentation to increase diversity which I would like to incorporate within my framework. Hence I would like to leverage the dataset provided by ADNI to facilitate my research |
Additional Investigators |