Speakers: Jiwoong Choi, PhD

Jiwoong Choi, PhD

Research Assistant Professor
Division of Pulmonary, Critical Care, and Sleep Medicine in the Department of Internal Medicine
University of Kansas School of Medicine

 

Jiwoong Choi is a Research Assistant Professor of the Division of Pulmonary, Critical Care, and Sleep Medicine in the Department of Internal Medicine at the University of Kansas School of Medicine since January 2020, Affiliate Assistant Professor at the Bioengineering Program of the University of Kansas, and Adjunct Professor at the Department of Mechanical Engineering, the University of Iowa. Dr. Choi received the B.S. and M.S. degrees in Mechanical Engineering at Seoul National University in 2000 and 2005, respectively, and the Ph.D. degree in Mechanical Engineering at the University of Iowa in 2011. Dr. Choi has a transdisciplinary career path, starting with Mechanical Engineering and further experiencing Biomedical Engineering and Radiology, and currently Pulmonary, Critical Care, and Sleep Medicine. Dr. Choi studied turbulent flow simulation for M.S., and since the Ph.D. program, his research focuses on quantitative lung CT imaging and computational lung modeling, using cross-volume and cross-time image matching via nonrigid image registration, computational fluid dynamics (CFD) simulations, and more computational analysis, processing terabyte-scale data for each project. He uses machine learning and deep learning approaches for physiological and pathophysiological interpretation and prediction of multiscale lung structural and functional features in lung health and diseases including asthma, chronic obstructive pulmonary disease (COPD), interstitial lung disease (ILD), COVID-19, lung cancer, environmental lung diseases, and so on, of human and animal models.

See What Happens in Your Lung: Quantitative CT, Computational Physics, and Machine Learning

The lung is a major organ to maintain the life of human body. However, due to its complex structure and function with the multiscale nature and presence of air, comprehensive understanding of the lung has been limited. For the past decades, computed tomography (CT) imaging and quantitative CT (qCT) analysis technologies have been rapidly advanced. CT-based computational physics modeling including computational fluid dynamics (CFD) simulations can now add more information of subject-specific, disease-specific, and phenotype-specific characteristics in air flow and inhaled particle deposition, without additional burden for patients. Addition of machine learning approaches such as dimensionality reduction, clustering, classification, prediction, and feature importance analysis helps draw more concrete interpretation to characterize complex structure-function relationship from the numerous quantitative features in lung health and disease, providing imaging biomarkers and phenotypes. Integration of qCT imaging, computational physics modeling including CFD airflow and particle simulations, and machine learning with demographics, clinical outcomes, and other lab data provides new understanding of clinical and subclinical lung physiology and pathophysiology. Applied studies include asthma, chronic obstructive pulmonary disease (COPD), interstitial lung disease (ILD), and normal-appearing subjects, in conjunction with aging, obesity, and environmental exposure.