B0889
Title: Challenges in data harmonization for Positron emission tomography (PET) imaging studies of Alzheimer's disease
Authors: Dana Tudorascu - University of Pittsburgh (United States) [presenting]
Abstract: Multisite imaging studies increase statistical power and enable the generalization of research outcomes; however, due to the variety of imaging acquisition, different PET tracer properties and inter-scanner variability hinder the direct comparability of multi-scanner PET data. The PET imaging field is lagging behind in terms of harmonization methods due to the complexity associated with the combination of different tracers and different scanners. Samples of cognitively normal participants, mild cognitively impaired, and Alzheimer's disease subjects are investigated in two major multisite studies of Alzheimer's disease. Challenges and solutions are presented associated with different PET tracer analysis and harmonization techniques including simple imaging standardization, ComBat and deep learning methods. Regions of interest differences are shown in PET outcome measures before and after the harmonization.
