Junghwa Kang
Ph.D Candidate
Department of Biomedical Engineering, Hankuk University of Foreign Studies
Embedded Files
I am a Ph.D student advised by Professor Yoonho Nam, at Department of Biomedical Engineering, Hankuk University of Foreign Studies (HUFSAIM Lab)
My research focuses on developing computational methods for reliable quantitative analysis of brain MRI, with particular emphasis on neonatal and infant neuroimaging. I investigate how developmental variation, imaging characteristics, and limited reference information affect quantitative MRI analysis, and develop deep-learning approaches for robust segmentation and measurement of brain structures. My current research focuses on the choroid plexus and perivascular spaces, with methodological interests in development-aware learning, anatomy-informed supervision, and cross-modal MRI analysis.
Developing Brain MRI — quantitative analysis of neonatal and infant brain MRI
Quantitative Neuroimaging — structural and morphological characterization of brain anatomy
Deep Learning for Medical Image Analysis — segmentation and automated MRI quantification
Development-Aware Learning — modeling developmental variation
Cross-Modal & Limited-Supervision Learning — leveraging complementary contrasts and imperfect references
Neurofluid-Associated Structures — Choroid plexus, and perivascular spaces
Contact
Contact
Education
Education
🎓 Ph.D, Hankuk University of Foreign Studies, 2022 ~ Present
Hankuk University of Foreign Studies
Advisor: Prof. Yoonho Nam
🎓 MS, Hankuk University of Foreign Studies, 2020~2022
Hankuk University of Foreign Studies
Advisor: Prof. Yoonho Nam
🎓 BS, Double Major in Division of Computer & Electronic Systems Engineering and Department of Biomedical Engineering, 2016 ~ 2020
Hankuk University of Foreign Studies
🎉 Recent News
[2026/5/9] ISMRM 2026 Summa Cum Laude
[2025/10/31] Present ICMRI 2025 Education session (Automatic Perivascular Space Quantification Method)
💡 Recent Conference
Age-Conditioned Neonatal Choroid Plexus Segmentation using Adaptive Conditional Instance Normalization
J Kang et al. Hankuk University of Foreign Studies, Korea
ISMRM, 2026, Oral Presentation (Summa Cum Laude)
Prediction of breast cancer recurrence based on automatically extracted quantitative MR features
J Kang et al. Hankuk University of Foreign Studies, Korea
ISMRM, 2025, Oral Presentation (Magna Cum Laude)
Automatic Lateral Ventricle and Choroid Plexus segmentation Method in Infant Brain MR Images
J Kang et al. Hankuk University of Foreign Studies, Korea
ISMRM, 2025, Digital Poster
💡 Publication
• Kang, J., Kim, H. G., Shin, N. Y., & Nam, Y. (2026). Automatic lateral ventricle and choroid plexus segmentation method in infant brain MR images. BMC Medical Imaging link
• Kang, J., Bak, D., Shin, N. Y., Kim, H. G., & Nam, Y. (2026). Improved BG‐PVS Quantification in Infant Brain MRI Using Anatomy‐Informed Pseudo‐Labels for Joint BG and PVS Segmentation. Journal of Magnetic Resonance Imaging. link
• Park, G. E., Kim, S. H., Nam, Y., Kang, J., Park, M., & Kang, B. J. (2024). 3D Breast Cancer Segmentation in DCE‐MRI Using Deep Learning with Weak Annotation. Journal of Magnetic Resonance Imaging. link
• Kim, H., Jang, J., Kang, J., Jang, S., Nam, Y., Choi, Y., ... & Kim, B. S. (2022). Clinical implications of focal mineral deposition in the globus pallidus on CT and quantitative susceptibility mapping of MRI. Korean Journal of Radiology, 23(7), 742. link
• Nam, Y., Choi, Y., Kang, J., Seo, M., Heo, S. J., & Lee, M. K. (2022). Diagnosis of nasal bone fractures on plain radiographs via convolutional neural networks. Scientific Reports, 12(1), 21510. link
• Kim, W., Shin, H. G., Lee, H., Park, D., Kang, J., Nam, Y., ... & Jang, J. (2022). χ-Separation Imaging for Diagnosis of Multiple Sclerosis versus Neuromyelitis Optica Spectrum Disorder. Radiology, 220941. link
• Kang, J., & Nam, Y. (2022). Applications of Artificial Intelligence in MR Image Acquisition and Reconstruction. Journal of the Korean Society of Radiology, 83(6), 1229-1239. link
• Lee, J. H., Kang, J., Oh, S. H., & Ye, D. H. (2022). Multi-Domain Neumann Network with Sensitivity Maps for Parallel MRI Reconstruction. Sensors, 22(10), 3943. link
• Kang, J., Kim, H., Kim, E., Kim, E., Lee, H., Shin, N. Y., & Nam, Y. (2021). Convolutional Neural Network-Based Automatic Segmentation of Substantia Nigra on Nigrosome and Neuromelanin Sensitive MR Images. Investigative Magnetic Resonance Imaging, 25(3), 156-163. link
• Nam, Y., Park, G. E., Kang, J., & Kim, S. H. (2020). Fully Automatic Assessment of Background Parenchymal Enhancement on Breast MRI Using Machine‐Learning Models. Journal of Magnetic Resonance Imaging. Link / GitHub
💡 Awards & Honor
• 2026 ISMRM Annual Meeting & Exhibition Summa Cum Laude
• 2025 ISMRM Annual Meeting & Exhibition Magna Cum Laude
• 2021, 2022, 2023, 2025 ISMRM Annual Meeting & Exhibition Stipend
• 2024 MICCAI Enlarged Perivascular Spaces Segmentation challenge 3rd Place
• 2024 ISMRM, Imaging Neurofluids Study group TRAINEE AWARD 2nd Place Award
• MICCAI 2021 MSSEG2 challenge participation. Presentation / ShortPaper
- Short paper: Segmentation of New Multiple Sclerosis Lesions in Longitudinal MRI Analysis Using a Multi-Stage 3D Patch-wise Deep Learning Algorithm
• MOAI 2020 Body morphometry AI segmentation challenge
Final ranking: 1st Place
• Healthcare AI Learning Platform (HeLP) Challenge 2019
Task: Traumatic lesion classification and detection
Final ranking: 1st Place
PPT / Presentation / GitHub
💡 Academic Activities
Reviewer
Reviewer
MICCAI 2024, 2025, 2026
TA
• Medical Image Processing & Laboratory using Artificial Intelligence (Fall, 2020 / 2021 / 2022 / 2023 / 2024)
• Signal and system (Spring, 2024)
• Biomedical Artificial Intelligence (Spring, 2021/2022/2023)
• Biomedical Probability & Statistics (Spring, 2020)
• Logic circuit & Lab (Spring, 2019)
Page updated
Google Sites
Report abuse