Visual-Driven Intelligence for Surgery
VDI Lab is a clinical AI group at the Chang Gung Memorial Hospital Burn Center, Linkou, founded in 2025 with AI teams from National Yang Ming Chiao Tung University and Chang Gung University. We develop quantitative measurement methods and AI models using image analysis, natural language processing and multimodal learning for bedside use.
Rooted in burn care, our work extends across rhinoplasty, craniofacial and microsurgical reconstruction.
Research pillars
Burn care
Automated assessment of burn area and depth, inhalation-injury risk prediction, and outcome research on the Chang Gung Research Database.
Rhinoplasty & craniofacial
Landmark-based morphometrics for rhinoplasty, and CBCT / 3D models for orthognathic planning and bad-split risk.
Microsurgical reconstruction
Perfusion imaging and deep learning for monitoring free-flap circulation.
Highlights
Burn wound segmentation
Deep-supervision UNet++ that outlines burn wounds on clinical photographs, as a first step toward objective TBSA and depth assessment.
Inhalation injury prediction
Machine-learning prediction of inhalation injury from admission data (Burns, 2023), now extended to multimodal deep learning.
Burn outcomes from CGRD
Outcome research on the Chang Gung Research Database — transfusion strategy, infection, length of stay and reconstructive burden — with rule-based NLP for extracting injury details from clinical notes.
Quantitative rhinoplasty
Landmark-based measurement of pre- and post-operative nasal form, with reliability-tested annotation tools, for reproducible aesthetic evaluation and outcome prediction.
Orthognathic bad-split prediction
CBCT and 3D-imaging models for predicting unfavorable fractures (bad splits) in sagittal split osteotomy, supporting orthognathic surgical planning.
Flap perfusion AI
Image-based assessment of free-flap circulation, from ICG fluorescence perfusion segmentation to a ResNet18 model that classifies flap status from a region of interest.