Jongwoo Kim, PhD
Applied Clinical Informatics Branch
Staff Scientist
jongkim@mail.nih.gov
Expertise and Research Interests:
Dr. Jongwoo Kim is a staff scientist at the Lister Hill National Center for Biomedical Communications at the United States National Library of Medicine (NLM), National Institutes of Health (NIH). He received his Ph.D. at the University of Missouri, Columbia, majoring in Computer Engineering and Computer Science. His research interests include deep (machine) learning, computer vision, image processing, Fuzzy theory, and document image processing. Currently, he is developing several algorithms with the National Eye Institute (NEI) and other Institutes using deep learning and image processing technologies to detect and diagnose retinal diseases and abnormality from fundus, optical coherence tomography (OCT), and fluorescein angiography (FA) images. His current works focuses on three areas: First, he works on improving diagnosis of glaucoma through automatic segmentation of optic disc and cup, and estimation of measures (Cup to Disc ratio, Rim to Disc ratio, etc.) from fundus images. Second, he works on the classification and segmentation of OCT images based on diseases and defects. Third, he researches automatic segmentation of leakages and blood vessels from FA images for uveitis.
Previously, Dr. Kim was involved in several projects such as Medical Article Recording System (MARS), Web-based Medical Article Recording System (WebMARS), Publisher Data Review System (PDRS), and In-Memory Processing for Publisher Online Articles (IMPPOA) to develop document processing systems for biomedical journal articles. He led a team to design, develop, and maintain web-based MARS that extracts bibliographic information from hard-copy journal articles to populate MEDLINE® using WCF services and Web-based GUIs. He also led a team to design and develop a web-based systems (WebMARS, PDRS, and IMPPOA) to extract bibliographic information from full text online journal articles in publishers’ websites and PubMed Central® for MEDLINE®. In his research on both projects, he also developed several key algorithms to automatically extract the bibliographic information using statistics and machine learning algorithms such as Fuzzy theory, SVM, Bayesian, and deep learning.
Dr. Kim is a member of the Institute of Electrical and Electronics Engineers (IEEE). He serves on the member of the Editorial Board of the International Journal of Imaging Systems and Technology (IMA). He also works as a reviewer for several journals related to the medical/biomedical image processing areas.
Publications:
Angara S, Kim J. Deep Ensemble Learning for Classification of Glaucoma from Smartphon Fundus Images. IEEE-CBMS 2024, pp. 412-417, Guadalajara, Mexico, June 2024. DOI Bookmark: 10.1109/CBMS61543.2024.00074.Kim J, Tran L. Ensemble Convolutional Neural Networks for the Classification and Visualization of Retinal Diseases in Optical Coherence Tomography Images. IEEE-CBMS 2023, pp. 123-28, L'Aquila, Italy, June 2023.
Kim J, Tran L, Peto T, Chew EY, HN. Deep Learning and Ensemble Method for Optic Disc and Cup Segmentation. IEEE CIBCB 2022, August 15-17, 2022. https://doi.org/10.1109/CIBCB55180.2022.9863022.
Young L, Kim J, Yakin M, Lin H, Dao D, Kodati S, Sharma S, Lee A, Lee C, Sen, HN. Automated Detection of Vascular Leakage in Fluorescein Angiography – A Proof of Concept. TVST, 2022, Vol. 11, No. 7, Article 19; https://tvst.arvojournals.org/article.aspx?articleid=2783507.