Papers
1
Total Citations
2
H-Index
1
About
J. Desternes is a rising researcher in the field of surgical robotics and medical image computing, with a primary focus on developing autonomous and semi-autonomous systems for robot-assisted surgery. Their most significant contribution to date is the introduction of a landmark-free, automatic digital twin registration framework for robot-assisted partial nephrectomy, detailed in their 2025 paper. This work proposes a generic end-to-end model that eliminates the need for manual landmark identification, a critical bottleneck in real-time surgical navigation. By enabling seamless alignment of preoperative models with intraoperative anatomy, Desternes’ approach enhances the precision of tumor resection while reducing cognitive load on surgeons. Though early in their career, with their flagship paper already garnering 2 citations, the work represents a foundational step toward fully autonomous surgical workflows. Desternes’ research sits at the intersection of computer vision, deep learning, and urologic oncology, promising to improve patient outcomes through smarter, more adaptive robotic tools. Their innovative methodology is poised to influence future developments in digital twin technology for minimally invasive surgery.
Research Focus
Key Achievements
Top Papers
- 1