Jae Wook Cho

The paper introduces a framework to quantify and optimize measurement reliability for studying individual differences in neuroscience and clinical research.

The paper examines how concatenating fMRI data affects the reliability of functional connectomics, finding that concatenating multiple scans under the same state improves reliability compared to a single long scan.

The paper develops a transfer-learning U-Net model for brain extraction in non-human primates using human data, achieving better performance than traditional methods and popular MRI packages.