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: | Bhavana Prakash |
| Institution: | New York University |
| Department: | Electrical and Computer Engineering |
| Country: | |
| Proposed Analysis: | I, with two other team members are trying to replicate the work of E. Jun, S. Jeong, D.-W. Heo, and H.-I. Suk titled, “Medical Transformer: Universal Brain Encoder for 3D MRI Analysis.” (arXiv: 2104.13633 [cs]). Our objective is to build a transfer learning network, namely Medical transformer, which uses a multi-view approach on sequence of 2D image slices to model a 3D image. The aim is to treat each slice along x, y, and z axes as a token and do masked token prediction as the pre-training regime to train 3 separate branches of the network, each for one of x, y, and z direction. The skeleton of the network contains a convolutional encoder, a transformer and a prediction network. The convolutional encoder and transformers are pre-trained in a self supervised learning manner on MRI data to finetune the network, and integrated with a prediction network. To perform Alzheimer’s disease (AD), mild cognitive impairment (MCI), and cognitively normal (CN) detection, we need T1-weighted structural MRI scans from ADNI dataset |
| Additional Investigators |
