Tuong Do
Papers
1
Total Citations
2
H-Index
1
About
Tuong Do is a leading researcher at the intersection of federated learning and medical imaging, with a primary focus on advancing endovascular surgery through artificial intelligence. His most influential work, "FedEFM: Federated Endovascular Foundation Model with Unseen Data" (2025), tackles the critical challenge of precisely segmenting catheters and guidewires in X-ray images—a task essential for reducing intervention risks. By developing a federated foundation model, Do addresses the scarcity of labeled medical data, enabling robust performance even on unseen datasets. This innovative approach has already garnered 2 citations, signaling its growing impact in the field. Do’s contributions lie in bridging the gap between privacy-preserving machine learning and high-stakes clinical applications, offering a scalable solution for surgical tool detection. His work is particularly notable for its potential to enhance real-time guidance in minimally invasive procedures, making surgery safer and more efficient. For students and researchers, Tuong Do exemplifies how federated learning can unlock new frontiers in medical AI, where data scarcity and privacy constraints often hinder progress.
Research Focus
Key Achievements
Top Papers
- 1FedEFM: Federated Endovascular Foundation Model with Unseen Data2 citations · 2025