YOUNGUNG HAN is currently pursuing the Ph.D. degree with the Department of Computer Science and Engineering, Seoul National University, Seoul, Republic of Korea. He is a Research Assistant at the Intelligent Medical Systems and Imaging (IMSI) Laboratory, where his research focuses on developing advanced deep learning architectures for medical image analysis. His research interests lie in advanced deep learning architectures for 3D medical image analysis. Recently, he has been developing adaptive transformer architectures to detect subtle pathological features. He is also actively exploring generative AI frameworks and self-supervised learning strategies to address the challenges of data scarcity and class imbalance in clinical datasets.

Need more training data on my background? You can find the uncompressed version on my LinkedIn. I’m always looking for new nodes to add to my network.

Education

  • Ph.D. Candiate (ABD) in Computer Science and Engineering

    Seoul National University

Recent Publications

  • LOSA-NET: A LOCALIZED AND SCALE-ADAPTIVE NETWORK FOR BOUNDARY-SENSITIVE PREDICTION OF PERINEURAL INVASION IN 3D MRI, IEEE ISBI 2026
  • MMA-FORMER: MULTI-WINDOW MIXTURE-OF-HEAD ATTENTION TRANSFORMER FOR ADAPTIVE PNI PREDICTION IN 3D MRI, IEEE ISBI 2026
  • 3D-LLDM: Label-Guided 3D Latent Diffusion Model for High-Resolution Synthetic Medical Imaging, IEEE ISBI 2026
  • GLARE: GPU-Accelerated 3D CT Vision-Language Reasoning via Efficient Anatomical Boundary Guidance, NVIDIA GTC 2026
  • RAPIDS: Real-time Accelerated Pipeline for Intelligent Dental Segmentation, NVIDIA GTC 2026
  • NeoNet: An End-to-End 3D MRI-Based Deep Learning Framework for Non-Invasive Prediction of Perineural Invasion via Generation-Driven Classification, Workshop on Health Intelligence (W3PHIAI), AAAI 2026 (Oral)
  • MAESIL: Masked Autoencoder for Enhanced Self-supervised Medical Image Learning, IEEE ICEIC 2026
  • CIPHER: Counterfeit Image Pattern High-level Examination via Representation for GAN and Diffusion Discriminator Learning, IEEE ICCE-Asia 2025
  • FOSCU: Feasibility of Synthetic MRI Generation via Duo-Diffusion Models for Enhancement of 3D U-Nets in Hepatic Segmentation, IEEE APCCAS 2025