Synthesizing study-specific controls using generative models on open access datasets for harmonized multi-study analyses

Abstract: Neuroimaging consortia can enhance reliability and generalizability of findings by pooling data across studies to achieve larger sample sizes. To adjust for site and MRI protocol effects, imaging datasets are often harmonized based on healthy controls. When data from a control group were not collected, statistical harmonization options are limited as patient characteristics and acquisition-related variables may be confounded. Here, in a multi-study neuroimaging analysis of Alzheimer's patients and controls, we tested whether it is possible to generate synthetic control MRIs. For one case-control study, we used a generative adversarial model for style-based harmonization to generate site-specific controls. Downstream feature extraction, statistical harmonization and group-level multi-study case-control and case-only analyses were performed twice, using either true or synthetic controls. All effect sizes using synthetic controls overlapped with those based on true study controls. This line of work may facilitate wider inclusion of case-only studies in multi-study consortia.