Hosung Kim

Assistant Professor of Neurology

Hosung   Kim

Research Topics

  • Neurodevelopment, neonatal brain imaging
  • Machine learning, deep learning in clinical neuroscience
  • Brain imaging quality assessment & control
  • Prediction of outcome in acute & chronic stroke patients using machine learning
  • Neuroimaging processing and statistical analyses

Research Images

Analysis of infant brain development

Research Overview

My ultimate research goal is to develops a universal imaging analytic platform to quantitatively analyze neurodevelopment and neurodegeneration at various ages in healthy and disease conditions. This needs a broad range of expertise in pattern recognition techniques as well as of experience in neuroscience research.
In my lab, there has been a logical progress from development of medical image analysis techniques, to modeling of trajectory of brain development. We are applying various analytic frameworks, including cortical morphometry, voxel-based morphometry, deformation-based morphometry and structural network analysis, to assessment of brain structures in healthy conditions as well as in pathological conditions that often present anatomical variations beyond the range of normal structures. We are also advancing these analytic techniques by combining the resulting features or measurements with pattern recognition algorithms such as the deep convolutional network-based learning or the random forest classifier. This innovative technology is expected to efficiently analyze BIG DATA and greatly improve our understanding of a given disease spectrum or patterning of brain changes for a given disease population.

Contact Information

Mailing Address USC Stevens Neuroimaging and Informatics Institute
Keck School of Medicine of USC
University of Southern California
2025 Zonal Ave.
Los Angeles, CA 90033
Office Location 2nd floor, USC Stevens Neuroim
Office Phone (323) 865-1753
Lab Location
Lab Phone
Office Location 2nd floor, USC Stevens Neuroim


Selected Publications

View a complete Google Scholar search