ADNI data is made available to researchers around the world. As such, there are many active research projects accessing and applying the shared ADNI data. To further encourage Alzheimer’s disease research collaboration, and to help prevent duplicate efforts, the list below shows the specific research focus of the active ADNI investigations. This information is requested annually as a requirement for data access.
| Principal Investigator | |
| Principal Investigator's Name: | Murat Ayhan |
| Institution: | University of Louisiana at Lafayette |
| Department: | Center of Advanced Computer Studies |
| Country: | |
| Proposed Analysis: | Neuro-imaging techniques such as fMRI and PET scans are good sources of information for AD diagnosis. However, it takes domain-experts to examine the imagery in order to make informed decisions about the patients. This process is error-prone due to human factor. In this regard, we are planing to investigate various techniques of machine learning to uncover underlying patterns relevant to the progression of AD. The ultimate goal is to come up with the model capable of discerning Clinical Dementia Ratings (CDRs) of patients. In large datasets, unsupervised feature learning methods are used to derive high quality features that describe data instances. Using such features, generative models can be utilized for analyzing the patterns that distinguish CDRs of patients. On the other hand, discriminative models are good at directly modeling input-output mappings given the patients' scan data. As a result, they may enable accurate diagnosis of AD. Using data from ADNI repositories, we would like to conduct experiments in order to evaluate several methods that fall into aforementioned categories. |
| Additional Investigators | |
| Investigator's Name: | Ashish Gupta |
| Proposed Analysis: | Neuro-imaging techniques such as fMRI and PET scans are good sources of information for AD diagnosis. However, it takes domain-experts to examine the imagery in order to make informed decisions about the patients. This process is error-prone due to human factor. In this regard, we are planing to investigate various techniques of machine learning to uncover underlying patterns relevant to the progression of AD. The ultimate goal is to come up with the model capable of discerning Clinical Dementia Ratings (CDRs) of patients. In large datasets, unsupervised feature learning methods are used to derive high quality features that describe data instances. Using such features, generative models can be utilized for analyzing the patterns that distinguish CDRs of patients. On the other hand, discriminative models are good at directly modeling input-output mappings given the patients' scan data. As a result, they may enable accurate diagnosis of AD. Using data from ADNI repositories, we would like to conduct experiments in order to evaluate several methods that fall into aforementioned categories. |