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: | wei li |
| Institution: | Shandong Normal University |
| Department: | School of Information Science and Engineering |
| Country: | |
| Proposed Analysis: | Dear ADNI Data Access Committee, I am writing to apply for access to the ADNI dataset for my research on medical image segmentation. My proposed analysis aims to investigate the effectiveness of deep learning algorithms in segmenting brain structures in MRI scans of Alzheimer's disease patients. The main objectives of my study are to improve the accuracy and efficiency of automated brain segmentation, which can potentially aid in the early diagnosis and monitoring of Alzheimer's disease progression. In my analysis, I plan to utilize the T1-weighted MRI scans from the ADNI dataset, specifically focusing on the baseline scans of patients with Alzheimer's disease. I will employ a deep learning framework, leveraging Transformer and advanced segmentation techniques, such as U-Net or similar architectures, to extract precise brain structures, including the hippocampus, ventricles, and cortical regions. The proposed analysis will involve several steps. Firstly, I will preprocess the MRI scans by performing intensity normalization and spatial registration to ensure consistent and aligned data. Next, I will train the deep learning model using a combination of the ADNI dataset and publicly available labeled brain segmentation datasets. The model will be optimized using a combination of focal loss and Dice loss, balancing the importance of accurate segmentation and handling class imbalance. I will also implement data augmentation techniques to enhance the model's generalization capability. To evaluate the performance of the segmentation model, I will conduct quantitative assessments, including Dice similarity coefficient (DSC), Hausdorff distance, and volume overlap metrics. Additionally, I plan to compare the deep learning approach with existing state-of-the-art segmentation methods to demonstrate its superiority in terms of accuracy and computational efficiency. I anticipate that the proposed analysis will provide valuable insights into the automated segmentation of brain structures in Alzheimer's disease patients, potentially contributing to the development of more effective diagnostic tools and treatment monitoring strategies. I assure you that all data obtained from the ADNI dataset will be handled with the utmost care, ensuring strict adherence to data protection and privacy guidelines. Thank you for considering my application. I am committed to conducting rigorous and ethical research, and I appreciate the opportunity to access the ADNI dataset for advancing our understanding of Alzheimer's disease through medical image analysis. Please let me know if there are any additional requirements or procedures I need to follow. Sincerely, Wei Li |
| Additional Investigators |
