Comparison of image-based and statistical approaches for brain volumetry harmonization

Image harmonization approaches have been proposed for reducing the variation of brain image measurements in studies involving acquisitions from multiple scanner protocols and hardware. This study compares two harmonization methods, DeepHarmony, a deep learning-based image synthesis approach, and ComBat, a statistical batch correction tool, based on their ability to yield consistent brain volume measurements from two different T1-weighted acquisitions. Our study showed that DeepHarmony outperformed the ComBat approach, although both approaches significantly improved consistency when compared to unharmonized images.