Hyun Seo Lee

Biomedical Engineering PhD student, Johns Hopkins University.

prof_pic_hsl.png

Hi, I’m Hyun Seo (Emily) Lee, a PhD student in Biomedical Engineering at Johns Hopkins University, advised by Nicholas Durr in the Computational Biophotonics Lab. I work at the intersection of machine learning and medical imaging, building diagnostic and sensing systems that are efficient on edge devices, robust across patient populations, and aware of their own uncertainty.

What I work on

  • Computational optical imaging: a smartphone-based nailfold capillaroscopy system for non-invasive hemoglobin estimation, where skin tone, finger curvature, and illumination are treated as first-class design constraints rather than nuisances to correct for later.
  • Adaptive inference for medical vision: efficient Vision Transformers that decide, per image, when to reduce tokens and when to exit early, allocating compute by difficulty while preserving diagnostic accuracy.
  • Robust, equitable medical AI: methods that hold up across skin tones and imaging conditions, from exposure-aware acquisition to skin-tone-aware augmentation.

More about me →

selected publications

  1. MIDL
    Adaptive Inference for Medical Vision Transformers: Token Reduction or Early Exit?
    Ji Young Byun, Hyun Seo Lee, Jordan M Shuff, and 3 more authors
    In Medical Imaging with Deep Learning (MIDL), 2026
    *Equal contribution.
  2. ARVO
    Patient Perspectives on Home Tonometry Among United States and Indian Populations
    Valerie W. Wong, Elizabeth Ciociola Kelly, Elliott Leow, and 11 more authors
    Investigative Ophthalmology & Visual Science, 2026