About me
I am an AI Researcher at GNEWSOFT and a Research Assistant at the Medical Imaging Lab (IMSI), CAPP Lab, Seoul National University. My research is supervised by Prof. Nam-Joon Kim, Prof. Hyuk-Jae Lee, and Prof. Woo Kyoung Jeong (Radiologist, Samsung Medical Center). I collaborate closely with NVIDIA researchers on cutting-edge medical AI projects.
My current research focuses on:
- Medical Image Analysis: 3D MRI synthesis, segmentation-guided ControlNet pipelines, and clinical AI applications
- Generative AI: Diffusion models, foundation models, and multimodal deep learning
- Foundation Models: HyperspectralMAE, LLaMA fine-tuning, and vision-language models
- Hyperspectral Imaging: Spectral analysis, anomaly detection, and pixel-wise classification
I am passionate about developing AI solutions that can make a real impact in medical diagnostics and patient care. I lead the SUDAL Medical Imaging Team and have built the official IMSI Lab website from the ground up. The IMSI Lab is a specialized medical imaging laboratory under Seoul National University’s CAPP Lab.
I believe AI should serve humanity, especially in healthcare where it can save lives! 🏥🤖
Feel free to reach out if you’re interested in medical AI, generative models, or collaborative research opportunities!
Current Research & Leadership
Research Focus
I conduct research on multimodal medical AI across diverse clinical imaging domains, including tumor-aware liver MRI synthesis, liver tumor classification, brain MRI biomarker prediction (IDH mutation, 1p/19q codeletion, WHO grade), tooth detection and dental caries segmentation, prostate cancer classification, and TNM staging of liver tumors.
Lambda Course
I organize and lead a weekly research seminar held every Saturday (12:00–14:00), conducting structured discussions and reviews of approximately six state-of-the-art AI and medical imaging papers per session.
Platform Development
I solely built and maintain the official IMSI Lab website, providing a centralized platform for research highlights, publications, member profiles, and project documentation, significantly improving lab visibility and internal communication.
International Collaborations
TEAM CEUS (NVIDIA Collaboration)
Work in direct technical collaboration with NVIDIA researchers, including Ping Shu Ho (Cliff) and Ivan Au-Yeung, on diffusion-based contrast-enhanced ultrasound (CEUS) reconstruction, noise reduction, and real-time enhancement models optimized for NVIDIA GPU computing pipelines.
TEAM PNI (NVIDIA Collaboration)
Conduct joint model development with Ka-Chun (Charles) Cheung, Ph.D. and Ginny Wong, Ph.D., focusing on physiology-informed MRI generation, neural parameterization, and multimodal generative imaging aligned with NVIDIA’s biomedical simulation research.
Multi-institutional Partnerships
Conduct collaborative research with multiple clinical and industrial partners including Samsung Medical Center (SMC), Severance Hospital, NVIDIA Hong Kong, and NVIDIA Taiwan, focusing on generative medical imaging, multimodal clinical AI, and large-scale synthetic medical data generation.
Education
Master of Science in Artificial Intelligence (GPA: 4.03/4.5)
Kookmin University | Sep 2022 - Feb 2024
- Specialized in generative AI and deep learning with focus on multimodal data integration
Bachelor of Science in Computer Science (GPA: 4.12/4.5)
Hankyong National University | Mar 2018 - Aug 2022
- Awarded full scholarship for academic excellence
- Completed 158 credits (graduation requirement: 130)
Recent News
- February 2026: Selected for presentation at IEEE ICEIC 2026 with MAESIL paper
- January 2026: MAESIL paper on enhanced self-supervised medical image learning accepted
- December 2025: Started collaboration with Samsung Medical Center on AI-driven radiology solutions
- November 2025: 3D-LLDM paper accepted at IEEE ISBI 2025
- October 2024: Joined GNEWSOFT as AI Researcher, developed HyperspectralMAE achieving SOTA performance
- September 2025: FOSCU paper accepted at IEEE APCCAS 2025 - presented in Busan
- September 2024: Started research at Medical Imaging Lab, Seoul National University
Recent Publications
Under Review (2026)
-
TIME: 2.5D IDH-predictive Multimodal Ensemble for Glioma Subtyping [Code]
Int. Conf. Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2026 (Under Review) -
MATHENA: Mamba-based Tooth Hierarchical Estimator and Evaluation Network [Code]
Int. Conf. Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2026 (Under Review)
Published (2026)
-
3D-LLDM: Label-Guided 3D Latent Diffusion Model [Poster] [Slides]
IEEE Int. Symp. Biomedical Imaging (ISBI) 2026 Oral Presentation -
MAESIL: Masked Autoencoder for Enhanced Self-supervised Medical Image Learning [Code] [Poster]
IEEE Int. Conf. Electronics, Information, and Communication (ICEIC) 2026
Professional Experience
- AI Researcher at GNEWSOFT (Oct. 2024 – Present)
- Medical Imaging Team Lead at OUTTA (Jul. 2023 – Present)
- AI Researcher at Weatherpia (Mar. 2024 – Aug. 2024)
- Data Scientist at LG Uplus (Jan. 2024 – Mar. 2024)
- AI Instructor at SK Telecom (Dec. 2023)
- AI Software Engineer at AI O2O Inc. (Aug. 2023– Dec. 2023)
- Data Analyst at OESON (Jan. 2023– Mar. 2023)
- Software Engineer at NuriFlex Holdings Inc. (Nov. 2021– Dec. 2022)
- Junior Developer at AST Global (Oct. 2020– Apr. 2021)
Teaching & Mentoring
- Taught deep learning and Python bootcamps for 450+ participants (2023) and 650+ participants (2024)
- Lead weekly journal clubs on medical imaging at IMSI Lab
- Mentor junior researchers across multimodal medical AI projects
Contact
Email: khkim1729[at]gmail.com