PeopleofSuperintelligence

Researcher

Hongki Yoo

Hongki Yoo is a mechanical engineer who builds optical imaging catheters and machine-learning tools for diagnosing coronary artery disease. After degrees in mechanical engineering at KAIST and a research fellowship at the Wellman Center for Photomedicine at Harvard Medical School, he co-reported a dual-modality intra-arterial catheter in Nature Medicine in 2011 and led a lab at Hanyang University from 2012 to 2019. At KAIST, where he established the Biomedical Optics and Optical Metrology (BOOM) Lab in 2019, his team published an OCT-FLIm catheter with a machine-learning framework in 2021. He co-authored the first-in-human OCT-FLIm study of 40 patients in JAMA Cardiology in 2025 and a weakly supervised deep-learning method for lipid detection in spectroscopic OCT in 2026. He is a professor of mechanical engineering at KAIST, where the AI College lists his research area as biological data and biomedical AI.

Now at
KAIST
Badges

Timeline

  1. 2001–2007

    Mechanical engineering degrees at KAIST

    He earns a B.S. in mechanical engineering at KAIST in 2001, an M.S. in 2003 and a Ph.D. in 2007.

  2. 2008–2012

    Harvard fellowship and a dual-modality catheter

    He works as a research fellow and instructor at the Wellman Center for Photomedicine, Harvard Medical School and Massachusetts General Hospital, from 2008 to 2012. In 2011, he and Jin Won Kim report in Nature Medicine a catheter that combines optical frequency domain imaging with near-infrared fluorescence imaging for simultaneous microstructural and molecular imaging in vivo.

  3. 2012–2019

    A lab at Hanyang University

    He joins the Department of Biomedical Engineering at Hanyang University as an assistant professor in 2012 and becomes an associate professor in 2016. Until 2019, he leads the university's Biomedical Optics and Photomedicine Lab.

  4. 2019

    Founding the BOOM Lab

    He joins KAIST's Department of Mechanical Engineering in 2019 to establish and lead the Biomedical Optics and Optical Metrology (BOOM) Lab. His research topics include multimodal optical imaging, endoscopic imaging, optical coherence tomography, 3D metrology, and machine learning in optical imaging.

  5. December 2021

    An OCT-FLIm imaging catheter

    A team led by Yoo and Jin Won Kim of Korea University Guro Hospital develops a label-free OCT-FLIm system and a low-profile dual-modal catheter, published with Hyeong Soo Nam in JACC: Basic to Translational Science in December 2021. The catheter characterizes high-risk plaque features in beating swine hearts, and a machine-learning framework trained on histology automatically characterizes lipids and macrophages.

  6. May 2025

    First-in-human OCT-FLIm study

    JAMA Cardiology publishes the first-in-human study of intracoronary OCT-FLIm in May 2025, with Yoo among the authors. The study enrolls 40 patients undergoing coronary revascularization, and FLIm characterizes the molecular signatures of macrophages, healed plaques, superficial calcification and fibrosis.

  7. 2026

    Deep learning for lipid detection

    In 2026, he co-authors a Biomedical Optics Express paper on a weakly supervised deep-learning framework that detects and localizes lipid in spectroscopic OCT. Validated against histology of rabbit aortas, the model reaches an arc-level overlap agreement of 83.9%.

  8. Since September 2025

    Professor at KAIST

    He becomes a professor in KAIST's Department of Mechanical Engineering in September 2025. KAIST's AI College lists him as an adjunct professor, with biological data and biomedical AI as his research area and physics-informed AI and scientific machine learning as core AI competencies.

Career

  1. Since 2019KAISTAdjunct Professor, Founder and Lab Lead
  2. 2012–2019Hanyang UniversityAssistant Professor, Associate Professor
  3. 2008–2012Mass General BrighamResearch Fellow and Instructor

Education

  1. 2007KAISTPhD
  2. 2003KAISTM.S. in Mechanical Engineering
  3. 2001KAISTB.S. in Mechanical Engineering

From the biography.

  1. The United States employs an estimated 48% of people shaping AIIncludes KAIST. We estimate where the people shaping AI work today, how universities, companies and research institutes split across countries, and how country shares have changed since the 1960s.
  2. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes KAIST. We estimate where the people shaping AI studied and where their careers led. Massachusetts Institute of Technology leads with 467 former students, including 291 recorded doctorates.
  3. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes KAIST. We estimate where the people shaping AI worked when their most-cited papers appeared: the company share was 31% in 2020–2024 and 8% in 1970–1974, and Google led all organizations in 2020–2024.
  4. 44% of AI career moves go from one university to anotherIncludes KAIST. We estimate how 26,439 AI career moves link universities, companies, labs, nonprofits and government research centers, with decade counts, net flows and the top paths.

Colleagues

People with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Hongki Yoo yet. Send us a free-licensed photo.

  1. Professor | BOOM LAB boom.kaist.ac.kr. Checked 21 October 2026.
  2. Intra-arterial catheter for simultaneous microstructural and molecular imaging in vivo pmc.ncbi.nlm.nih.gov. Checked 21 October 2026.
  3. OSC Colloquium: Hongki Yoo, "Label-free Multimodal Optical Imaging for Translational Medicine" optics.arizona.edu. Checked 21 October 2026.
  4. Synergizing optical imaging and machine learning to diagnose coronary artery disease accurately breakthroughs.kaist.ac.kr. Checked 21 October 2026.
  5. Intracoronary Structural-Molecular Imaging for Multitargeted Characterization of High-Risk Plaque: First-in-Human OCT-FLIm ncbi.nlm.nih.gov. Checked 21 October 2026.
  6. Automated lipid detection in spectroscopic optical coherence tomography using a weakly supervised deep learning network pmc.ncbi.nlm.nih.gov. Checked 21 October 2026.
  7. Faculty | AX aicollege.kaist.ac.kr. Checked 21 October 2026.