Publications
Research contributions in medical imaging, computer vision, and AI systems
Journal Publications
Automatic and Quantitative Measurement of Alveolar Bone Level in OCT Images Using Deep Learning
Biomedical Optics Express
Developed deep learning methods for automatic measurement of alveolar bone levels in OCT images, providing a non-invasive alternative to traditional diagnostic methods.
Autonomous Computer Vision Development with Agentic AI
arXiv Preprint
Introduced agentic AI systems for autonomous computer vision development, demonstrating novel approaches to automated visual analysis.
Beyond the LUMIR challenge: The pathway to foundational registration models
Nature Machine Intelligence (under review)
Comprehensive study on foundational models for medical image registration, establishing benchmarks and methodologies for the field.
Learn2Reg 2024: New Benchmark Datasets Driving Progress on New Challenges
Learn2Reg 2024, Machine Learning for Biomedical Imaging (under review)
Comprehensive benchmarking study introducing new datasets and challenges for medical image registration, advancing the state-of-the-art in the field.
Dual-path Radiology Report Generation: Fusing Pathology Classification with Language Model
MICCAI 2025 Workshop on MLLMs in Clinical Practice
Novel approach to automated radiology report generation combining pathology classification with advanced language modeling techniques.
Conference Papers
TRACE: Textual Reasoning for Affordance Coordinate Extraction
ICCV 2025 Workshop on Knowledge-Intensive Multimodal Reasoning (Under Review)
Innovative approach to affordance coordinate extraction using textual reasoning in multimodal environments.
SPAR: Spatial Precision with Articulated Reasoning
ICCV 2025 Workshop on Multi-Modal Reasoning for Agentic Intelligence (Under Review)
Advanced spatial reasoning framework for articulated object understanding and manipulation.
Improving Foundation Models with Deep Layer Adapters for Medical Image Segmentation
RSNA 2024
Demonstrated the effectiveness of deep layer adapters in improving foundation model performance for medical image segmentation tasks.
Self-Supervised Learning Without Annotations to Improve Lung Chest X-Ray Segmentation
SPIE 2024
Novel self-supervised learning approach for chest X-ray segmentation that eliminates the need for manual annotations.
A Faster Deep learning-based Registration for Ear Surgery
EMBC 2022
Developed faster deep learning-based registration methods for enhanced precision in ear surgery navigation systems.
A Deep Learning-based Method for Tooth Segmentation on Panoramic Dental X-ray Images
EMBC 2021
Automated tooth segmentation method for panoramic dental X-rays using advanced deep learning architectures.
SANet: Self-Attention U-Net for Binary Tooth Segmentation
CICS 2021
Novel U-Net architecture with self-attention mechanisms for improved binary tooth segmentation performance.
CAPPU-Net: A Convolutional Attention Network with Pyramid Pooling for Segmentation of Middle and Inner Ear Structures in CT Images
EMBC 2021
Convolutional attention network with pyramid pooling for automated segmentation of ear structures in CT images.
SinusNet: Label-Free Segmentation of Maxillary Sinus Lesion in CBCT Images
Medical Imaging with Deep Learning 2022
Label-free segmentation approach for maxillary sinus lesions in CBCT images using deep learning.
A deep learning-based method for tooth segmentation on CBCT images affected by metal artifacts
EMBC 2021
Deep learning method for tooth segmentation in CBCT images with metal artifact challenges.
A Registration Method between Optical Tracker and Depth Camera Using Deep Learning
The Institute of Electronics and Information Engineers 2022
Deep learning-based registration method between optical tracker and depth camera for surgical navigation applications.
Patents
NAVIGATION SYSTEM USING SPRINT AND IMAGE REGISTRATION METHOD USING THE SAME
Patent No: 10-2021-0188978
Advanced navigation system utilizing sprint technology and sophisticated image registration methods for surgical applications. Part of Master's thesis: Development of an AI-Enhanced AR Navigation System for Precise Mastoidectomy.
Thesis & Academic Documents
Vision-Language Modeling for Medical Image Analysis
Ph.D. Dissertation Proposal, UCLA Physics and Biology in Medicine
Comprehensive research proposal outlining vision-language foundation models for medical imaging applications, including parameter-efficient fine-tuning and knowledge distillation strategies.
Dissertation Committee:
- • Dr. Matthew S. Brown (Chair)
- • Dr. Dan Ruan (Co-Chair)
- • Dr. John M. Hoffman
- • Dr. Michael McNitt-Gray
- • Dr. Yong Jae Lee
Leveraging Foundation Models, Knowledge Distillation, and Pseudo-Labeling for Robust Lung Segmentation in Computed Tomography Scans
Ph.D. Qualifying Examination, UCLA Physics and Biology in Medicine
Qualifying examination demonstrating expertise in foundation models, knowledge distillation, and pseudo-labeling techniques for medical image segmentation, specifically focusing on lung segmentation in CT scans.
Development of an AI-Enhanced AR Navigation System for Precise Mastoidectomy
M.E. Thesis, Seoul National University Interdisciplinary Program of Bioengineering
Comprehensive system integrating computer vision, deep learning, and augmented reality for surgical precision enhancement in ENT procedures. This foundational work established core competencies that inform current Vision-Language model research.
Selected Honors & Awards
1st place - SPIE 2024 Live Demonstrations Workshop
Mar 2024
Winner for "SimpleMind: A Cognitive AI software environment for aggregating deep learning algorithms and reasoning with their outputs" as voted by attendees.
3rd place - MOAI 2021 CT Segmentation task
Sep 2021
Achieved third place in the Body Morphometry A.I. Segmentation online challenge (Pseudolab).
3rd place - Oral Disease AI Contest
Mar 2021
Third place in classification task for oral disease detection using AI methods.
1st place - Healthhub datathon
Nov 2020
First place in CBCT Segmentation task with Team MIIL, demonstrating excellence in medical image analysis (Healthhub datathon).
Academic Service
Reviewer, MICCAI 2025
Reviewing papers in medical image computing and computer-assisted interventions.