Changmin Jeon, Ph.D.
Pioneering Deep Learning Architectures for Medical Diagnostics at the Graduate School of Artificial Intelligence.
Pioneering Deep Learning Architectures for Medical Diagnostics at the Graduate School of Artificial Intelligence.
As a distinguished Doctor of Philosophy from the Department of Artificial Intelligence at Korea University, my mission is to harmonize high-level mathematical theory with practical clinical application. My doctoral journey focused on the optimization of neural networks for complex medical imaging environments.
My expertise lies in the integration of Group Normalization (GN) to stabilize training trajectories in high-resolution medical data, alongside the deployment of YOLO-based detection systems for real-time radiographic interpretation.
Advancing the frontiers of automated medical diagnostics through sophisticated AI paradigms.
Refining Convolutional Neural Networks with Group Normalization (GN) to eliminate batch-size dependency in critical diagnostics.
Leveraging YOLO variants for the instantaneous localization of anatomical pathologies in high-fidelity X-ray streams.
Utilizing Graph Neural Networks (GNN) to model the intricate spatial relationships between physiological landmarks.
Developing robust, highly generalizable classification frameworks for thoracic and musculoskeletal abnormality screening.
Strategic Academic Milestones (2026 - 2030)
"Intelligent Radiography: Deep Learning-driven Precision in Clinical Workflows."
"Batch-Independent Training Stability: Evaluating Group Normalization in Medical CNN Architectures."
"Relational Context in Radiography: Fusing GNN and YOLO for Spatial-Aware Abnormality Detection."
"Adaptive Detection Frameworks: Real-time X-ray Analysis using Multi-modal YOLO Integration."
"Unified Sovereign AI: Integrating Universal Graph Embeddings and Sophisticated Standardization for Healthcare."