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: | Long Xie |
| Institution: | University of Pennsylvania |
| Department: | Radiology |
| Country: | |
| Proposed Analysis: | Curing Alzheimer’s disease (AD) is one of the great challenges of our generation. It is generally accepted that interventions are likely to be most effective early in the disease course when symptoms are minimal if present at all. Indeed, recent clinical trials have moved towards targeting preclinical populations, i.e. cognitively normal individuals with evidence of beta-amyloid (Abeta) pathology, which is the earliest detectable phase of AD. But the cost of conducting clinical trials in people who may not develop symptoms of AD for many years can be prohibitive. This highlights a growing need for more effective biomarkers of AD, including biomarkers that can identify those most likely to respond to treatment (cross-sectional biomarker) and biomarkers that can detect slowing or reversal of AD-related changes due to treatment over in as short of a timeframe as possible (longitudinal biomarker). The focus of this project is to derive more sensitive and specific cross-sectional and longitudinal biomarkers for preclinical AD from structural magnetic resonance imaging (MRI), the imaging modality that provides the most direct evidence of neuritic and neuronal loss in neurodegenerative disease. Existing large datasets of T1-weighted (1x1x1 mm3 resolution) and high inplane resolution T2-weighted (0.4x0.4x2 mm3) MRI scans will be utilized. Part 1 will develop and validate an enhanced cross-sectional MRI biomarker tailored for detecting pathological change in preclinical AD using an advanced deep-learning algorithm to extract disease-related MRI appearance alterations that conventional computational methods overlook. In addition, we will develop a novel training scheme that allows for the interpretability of the method, crucial for clinical translation. Part 2 will apply state-of-the-art graph-theory analysis techniques to quantify the longitudinal change of the cross-sectional biomarker in part 1 to generate a novel longitudinal biomarker. Inherited from the proposed enhanced sensitivity and specificity of the cross-sectional biomarker, we hypothesize the proposed longitudinal measure will better track AD-specific disease progression in the earliest stage of the disease. Taken together, this project will optimize the sensitivity and specificity of structural biomarker to preclinical AD, providing a potentially critical screening tool and outcome measure to accelerate disease modification studies. |
| Additional Investigators |
