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: | Sheena Waters |
| Institution: | Queen Mary, University of London |
| Department: | Preventive Neurology Unit |
| Country: | |
| Proposed Analysis: | We aim to develop automated analysis for routinely acquired brain images to improve diagnosis, stratification, and prognosis in patients with memory problems. More specifically, we intend to evaluate a novel analysis platform which harnesses the power of modern Convolutional Neural Network (CNN) architectures. The CNN can generate imaging biomarkers that are highly sensitive to neuroinflammation and neurodegeneration. These can be used for performing diagnosis, subtyping, staging, outcome prediction, and characterisation in dementia, therefore allowing for personalised treatment planning, and delivery of value-based healthcare. Aside from the anticipated clinical benefits, robust and sensitive imaging markers of disease processes are also of great value to Pharma trials of potential therapeutic interventions. For example, they can support more cost-effective trial designs by requiring smaller sample sizes, or shorter time scales to ascertain treatment effects. They can also enable trials of novel therapeutics that target the earliest disease processes, which is critical for developing treatments aiming to slow or reverse neurodegeneration. We have the following key aims for this study: 1. Capture the requirements of the solution’s intended end-users (clinical and pharmaceutical); 2. Deliver an advanced minimum viable product of the proposed solution, which involves the integration of existing image analysis and computational modelling algorithms, as well as the development of new artificial intelligence driven components; 3. Adhere to software quality management standards (e.g., ISO 13485) and relevant NHSX recommendations; 4. Exemplify the solution's performance using retrospective data from publicly available MRI data (scans from ADNI, AIBL, and ADNIDOD). |
| Additional Investigators | |
| Investigator's Name: | Ross Callaghan |
| Proposed Analysis: | We aim to develop automated analysis for routinely acquired brain images to improve diagnosis, stratification, and prognosis in patients with memory problems. More specifically, we intend to evaluate a novel analysis platform which harnesses the power of modern Convolutional Neural Network (CNN) architectures. The CNN can generate imaging biomarkers that are highly sensitive to neuroinflammation and neurodegeneration. These can be used for performing diagnosis, subtyping, staging, outcome prediction, and characterisation in dementia, therefore allowing for personalised treatment planning, and delivery of value-based healthcare. Aside from the anticipated clinical benefits, robust and sensitive imaging markers of disease processes are also of great value to Pharma trials of potential therapeutic interventions. For example, they can support more cost-effective trial designs by requiring smaller sample sizes, or shorter time scales to ascertain treatment effects. They can also enable trials of novel therapeutics that target the earliest disease processes, which is critical for developing treatments aiming to slow or reverse neurodegeneration. We have the following key aims for this study: 1. Capture the requirements of the solution’s intended end-users (clinical and pharmaceutical); 2. Deliver an advanced minimum viable product of the proposed solution, which involves the integration of existing image analysis and computational modelling algorithms, as well as the development of new artificial intelligence driven components; 3. Adhere to software quality management standards and relevant NHSX recommendations; 4. Exemplify the solution's performance using retrospective data from publicly available MRI data. |
