Ho Sung Kim

Associate Professor of Research Neurology and Biomedical Engineering

Image of Ho Sung Kim
Is this your profile? Click to edit

Overview

My research spans an interdisciplinary cross-section of Medical Image Processing, Machine learning, and Neuroscience covering clinical neurology and neuropsychiatry. In the fields of medical image processing and analysis, I have studied on multicontrast image registration and segmentation, surface modeling of cortical/subcortical structures which are the prerequisite techniques to proceed the analysis of structural and functional brain imaging studies.
My projects that have been recently launched at USC-INI and USC-LONI include mainly three domains of the research field: 1) Prediction of neurodevelopmental outcome in neonates with various clinical conditions such as preterm birth, hypoxia-ischemia, and congenital heart disease: This project expands in line with my team’s expertise in neurodevelopment, neuroimaging, computational imaging feature modeling and machine learning (particularly DEEP learning); 2) Neuroimaging data quality controls (image QC): My team dedicates its efforts to implementation of online-based LONI-QC system that allows the public to evaluate their own data as well as to automated QC feature that will ultimately predict the accuracy of brain image post-processing and the sensitivity in the subsequently biological/clinical analysis to given target pathophysiology, and 3) Prediction of brain age and accelerated aging due to neurodegeneration: combination of brain imaging data and covolutional neural network-based deep-learning can estimate the brain age for individual images. extending this model with a statistical hazard model, we aim to determine risk scores for aging subjects who potentially develop a neurodegenerative disease.
In other clinical/neuroscientific applications, my team has applied various advanced analytic frameworks, including cortical morphometry, voxel-based morphometry, deformation-based morphometry and structural network analysis, to the assessment of brain structure in healthy conditions as well as pathological conditions, which often present anatomical variations beyond the range of normal structures.
My team continues to expand aforementioned techniques to the analysis of BIG DATA of brain imaging data to better understand mechanisms involved in various diseases and disorders such as stroke, epilepsy, dementia, sleep disorders, as well as long-term deafness and sudden hearing loss.

Awards

  • Baxter Foundation: Donald E. and Delia B. Baxter Foundation Faculty Fellowship Award, 2017
     – 2018
  • Canadian Institutes of Health Research: Banting Postdoctoral Fellowships, 2015
     – 2017
  • Fonds de la recherche en sante/ Health Research Funds in Quebec (FRSQ): Post-doctoral fellowship, 2014
     – 2016
  • Sleep: Sleep Research Society Abstract Excellence Award, 2013
  • ISMRM 24th Annual Meeting & Exhibition: Young Investigator / Trainee Stipends Award, 2016
  • 10th Annual Meeting of Korean Sleep Research Society: Best Poster presentation award, 2013
  • American Epilepsy Society (AES 2011): Young Investigator Travel Award, American Epilepsy Society (AES 2011) 2011
  • American Epilepsy Society (AES 2010): Young Investigator Travel Award, American Epilepsy Society (AES 2010) 2010
  • International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2011): Student Travel Award, International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2011) 2011
  • Fonds de la recherche en santé / Health Research Funds in Quebec (FRSQ): Doctoral Training Awards, 2009
     – 2010
  • McGill University: Fellowship for returning graduate students, 2007
  • Hanyang University: Excellent Student Scholarship, 1998
     – 2000

Education and Training

  • McGill University, Montreal QC, Canada — Ph.D. — Biomedical Engineering
  • Montreal Neurological Institute, Montreal QC, Canada — Postdoctoral fellow — Neuroimaging of Epilepsy
  • University of California, San Francisco, San Francisco CA — Postdoctoral fellow — Neurodevelopment, Clinical Neuroscience

Research Funding

  • Machine learning of multicontrast MRI features to predict neurodevelopmental outcome of preterm neonates
    Baxter Foundation · Jul 1, 2017 – Jun 30, 2018 · Role: Principal investigator

Publications

  • Associations between contralesional neuroplasticity and motor impairment through deep learning-derived MRI regional brain age in chronic stroke (ENIGMA): a multicohort, retrospective, observational study. Lancet Digit Health. 2026 Jan; 8(1):100942.. View in PubMed
  • Chronotype prior to shift work influences outcomes: resilience as a mediator of sleep and mental health. Sleep. 2025 Nov 10; 48(11).. View in PubMed
  • Generative diffusion model enables quantification of calibration-free arterial spin labeling perfusion magnetic resonance imaging data in an Alzheimer’s disease cohort. Alzheimers Dement (Amst). 2025 Oct-Dec; 17(4):e70214.. View in PubMed
  • Brain Age Is Longitudinally Associated With Sensorimotor Impairment and Mild Cognitive Impairment in Subacute Stroke. J Am Heart Assoc. 2025 Oct 21; 14(20):e041603.. View in PubMed
  • Classifying mild cognitive impairment from normal cognition: fMRI complexity matches tau PET performance. Alzheimers Dement (Amst). 2025 Jul-Sep; 17(3):e70159.. View in PubMed
  • An expanded subventricular zone supports postnatal cortical interneuron migration in gyrencephalic brains. Nat Neurosci. 2025 Aug; 28(8):1598-1609.. View in PubMed
  • Obstructive sleep apnea subtyping based on apnea and hypopnea specific hypoxic burden is associated with brain aging and cardiometabolic syndrome. Comput Biol Med. 2025 02; 185:109604.. View in PubMed
  • P-Wave Duration Is Associated With Aging Patterns in Structural Brain Networks. J Am Heart Assoc. 2024 12 03; 13(23):e035881.. View in PubMed
  • Comparative evaluation of interpretation methods in surface-based age prediction for neonates. Neuroimage. 2024 10 15; 300:120861.. View in PubMed
  • Fibrinogen inhibits sonic hedgehog signaling and impairs neonatal cerebellar development after blood-brain barrier disruption. Proc Natl Acad Sci U S A. 2024 Jul 30; 121(31):e2323050121.. View in PubMed