David Bouget

Papers

Total Citations

393

H-Index

About

David Bouget is a leading researcher at the intersection of computer vision and surgical robotics, with a primary focus on enhancing intraoperative perception and automated skill assessment. His most influential work, the 2016 review "Vision-based and marker-less surgical tool detection and tracking," has garnered 274 citations, establishing a foundational taxonomy for instrument localization in minimally invasive procedures. Bouget has made pivotal contributions to surgical data science, particularly through his work on unsupervised trajectory segmentation for gesture recognition in robotic training (115 citations). This research addresses the critical challenge of objectively assessing dexterity and procedural knowledge—two skills essential for surgical mastery—by enabling automated, in-depth analysis of surgical gestures. His exploration of 3D reconstruction of the retinal surface for robot-assisted eye surgery further demonstrates his commitment to pushing the boundaries of precision in microsurgical environments. By combining marker-less tracking with machine learning, Bouget’s work directly supports the development of intelligent surgical systems that can provide real-time feedback and objective performance metrics, ultimately aiming to improve patient safety and training efficacy in robotic surgery.