Research Interests

• Generative Model: Harmonization

  * The Generative Model is a model that learns given learning data to generate similar data that follows the distribution of learning data. There are several methods of generative models, among which I mainly study the Generative Adversarial Network (GAN).

  * With the proliferation of multi-site neuroimaging studies, there is a greater need for handling non-biological variance introduced by differences in MRI scanners and acquisition protocols. Such unwanted sources of variation, which we refer to as “scanner effects”, can hinder the detection of imaging features associated with clinical covariates of interest and cause spurious findings. So I consider cross-site MRI image harmonization based on a GAN.