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: | 魏 明阳 |
| Institution: | Henan Polytechnic University |
| Department: | College of Computer Science and Technology |
| Country: | |
| Proposed Analysis: | Accurate detection of Alzheimer's disease (AD) is essential for proper treatment and understanding the early signs of AD. However, the use of traditional methods and calibration criteria for clinical diagnosis of AD depends on subjective image interpretation and limited (deterministic) biomarkers. Alternatively, automated methods can be used to interrogate nerve cells and identify patterns associated with neurodegeneration and cognitive decline in an efficient and objective manner. Recently, Vision Transformers (ViT) has been proposed as an alternative to convolutional neural networks (CNN) and has been shown in computers to foreground vision tasks without using convolution and to interpret images as a series of patches. ViT was proposed to overcome the challenges of CNN-based approaches, such as localization and translation invariance. This process is inherited from the standard Transformer encoder for the natural language processing (NLP) domain. To date, the efficacy and performance of ViT has been evaluated on natural images. ViT is proposed to be used for automatic AD classification using magnetic resonance images (MRI). |
| Additional Investigators |
