Research

AgentMed: Evaluating GPT-5 AI Agents in Medicine
AgentMed Project

Project Objective:

To evaluate how successive advancements from base LLMs to autonomous GPT-5 agents impact clinical reasoning and diagnostic accuracy.

Large-Scale Models for Medical Image Quality Control
Medical Image Quality Control

Project Objective:

Develop a multimodal medical imaging quality control model that automatically assesses the acquisition quality of multi-site human images and supports clinical diagnosis, particularly assisting doctors with limited reading experience in resource-constrained region.

ToothFussion: Generate a completed tooth from crown information
ToothFussion Project

Project Objective:

To generate complete CBCT tooth structures from partial IOS crown information and textual descriptions, thereby reducing dental patients' exposure to CT radiation and lowering the risk of radiation-induced malignancies.