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: | Kathy Fan |
| Institution: | Stanford |
| Department: | Computer Science |
| Country: | |
| Proposed Analysis: | This work is for a course project. We are interested in evaluating various methods for visualizing classification decisions for deep learning models as applied to brain imaging and the diagnosis of Alzheimer’s Disease (AD). Research scientists in the AI/ML field tend to focus on classification accuracy. However, from an applications standpoint, medical professionals are often interested not only in the ability of the model to accurately assess an MRI, but also in the way the model reaches its decisions. Easy interpretation of neural network classification processes would not only increase the credibility of such models for use in the healthcare industry, but also potentially augment future research in the field for the disease by making explicit any yet-undiscovered relationships or disease patterns that the model picks up on. |
| Additional Investigators | |
| Investigator's Name: | Elissa Li |
| Proposed Analysis: | We are interested in evaluating various methods for visualizing classification decisions for deep learning models as applied to brain imaging and the diagnosis of Alzheimer’s Disease (AD). Research scientists in the AI/ML field tend to focus on classification accuracy. However, from an applications standpoint, medical professionals are often interested not only in the ability of the model to accurately assess an MRI, but also in the way the model reaches its decisions. Easy interpretation of neural network classification processes would not only increase the credibility of such models for use in the healthcare industry, but also potentially augment future research in the field for the disease by making explicit any yet-undiscovered relationships or disease patterns that the model picks up on. |
| Investigator's Name: | Darian Martos |
| Proposed Analysis: | We are interested in evaluating various methods for visualizing classification decisions for deep learning models as applied to brain imaging and the diagnosis of Alzheimer’s Disease (AD). Research scientists in the AI/ML field tend to focus on classification accuracy. However, from an applications standpoint, medical professionals are often interested not only in the ability of the model to accurately assess an MRI, but also in the way the model reaches its decisions. Easy interpretation of neural network classification processes would not only increase the credibility of such models for use in the healthcare industry, but also potentially augment future research in the field for the disease by making explicit any yet-undiscovered relationships or disease patterns that the model picks up on. |
