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: | Alex Berg |
| Institution: | Massachusetts Institute of Technology |
| Department: | Electrical Engineering and Computer Science |
| Country: | |
| Proposed Analysis: | Alzheimer's Disease (AD) is believed to consist of several subtypes. Identifying these subtypes -and their distinct neuroimaging, genomic, and cellular features- may be the key to targeted clinical intervention. Overall, our group aims to identify granular subtypes of AD through imaging genetics and representation learning. Firstly, based on the work of Zhou et al (2019), we aim to train a convolutional neural network (CNN)-based classifier to predict patients' AD-status from MRI images. Then, using the trained CNN's internal feature representations, we aim to project patients' MRI data to low-dimensional representations and perform fuzzy k-means clustering - each resulting cluster representing a possible AD subtype. Finally, validation of these possible subtypes will occur through sparse canonical correlation analysis (SCCA) of patient-level neuroimaging, genetic, and cognitive data. References: Zhou T, Thung KH, Zhu X, Shen D. Effective feature learning and fusion of multimodality data using stage-wise deep neural network for dementia diagnosis. Hum Brain Mapp. 2019 Feb 15;40(3):1001-1016. doi: 10.1002/hbm.24428. Epub 2018 Nov 1. PMID: 30381863; PMCID: PMC6865441. |
| Additional Investigators | |
| Investigator's Name: | William Li |
| Proposed Analysis: | Ditto |
| Investigator's Name: | Neil Deshmukh |
| Proposed Analysis: | Ditto |
