Doctor of Philosophy in Artificial Intelligence. Specializing in High-Precision Medical Object Detection and Advanced Normalization Paradigms.
Upon earning my Doctorate from the Graduate School of Korea University, I have focused on bridging the gap between sophisticated AI architectures and clinical radiology. My academic journey has been defined by a commitment to enhancing diagnostic accuracy through the fusion of deep learning and medical imaging expertise.
My core research involves leveraging Group Normalization (GN) to achieve batch-size independence and superior stability during the training of deep neural networks. I am particularly adept at implementing YOLO-based detection and GNN-driven anatomical modeling for advanced X-ray interpretation.
Designing customized Convolutional Neural Networks for high-throughput screening of pathological patterns.
Pioneering YOLO-based frameworks for the real-time identification of lesions in thoracic radiographs.
Implementing Group Normalization (GN) to optimize learning trajectories in large-scale medical data.
Exploiting structural anatomical knowledge via GNNs to improve multi-label diagnostic precision.
Annual SCI-Level Achievements (2026 - 2030)
Keynote: "Deep Learning-based Precision Diagnostics in Clinical Radiography."
"Enhancing Low-Dose X-ray Classification via Deep CNNs with Group Normalization (GN) Layers."
"Spatial Relation-Aware Pathology Detection: A Hybrid GNN and YOLO Approach."
"Real-time Multi-modal Pathological Detection using Optimized YOLO with Stable Normalization."
"Sovereign AI for Healthcare: Integrating Universal Graph Embeddings and Modern Standardization."