Papers
2
Total Citations
21
H-Index
2
About
Michel Duprez is pioneering the application of deep reinforcement learning to autonomous medical interventions, with a primary focus on cardiovascular procedures. His research addresses the critical challenge of guidewire navigation through complex vascular anatomies, a task that traditionally exposes both patients and clinicians to prolonged X-ray radiation. Duprez’s major contributions include developing a zero-shot reinforcement learning strategy for autonomous guidewire navigation, which enables trained models to adapt to unseen dynamic environments without additional retraining. His 2024 paper on this topic has already garnered 16 citations, reflecting its immediate impact in the field. In related work, he demonstrated autonomous guidewire navigation in dynamic environments (5 citations), further advancing the potential for reducing procedure times and radiation exposure. Duprez’s innovative approach bridges the gap between simulation-based training and real-world clinical application, positioning him as a rising figure in the intersection of robotics, machine learning, and interventional medicine. His work holds promise for transforming minimally invasive surgeries into safer, more efficient procedures.
Research Focus
Key Achievements
Top Papers
- 1
- 2Autonomous Guidewire Navigation in Dynamic Environments5 citations · 2024