Yael Refaely
Papers
2
Total Citations
29
H-Index
2
About
Yael Refaely is a researcher at the forefront of robotic-assisted minimally invasive surgery (RAMIS), specializing in surgical data science and motor learning for skill acquisition. Her work bridges the gap between complex surgical robotics and practical training methodologies, addressing critical challenges in automation and skill assessment. Refaely’s most influential paper, "Using Augmentation to Improve the Robustness to Rotation of Deep Learning Segmentation in Robotic-Assisted Surgical Data" (2019, 27 citations), pioneers data augmentation techniques to enhance deep learning models’ rotational robustness, enabling more reliable analysis of kinematic data from surgical procedures. This contribution is vital for advancing automated surgical assessment and system design. In her subsequent work, "Combining Time-Dependent Force Perturbations in Robot-Assisted Surgery Training" (2021), she explores how motor learning theories—traditionally based on simple movements—can be adapted to improve RAMIS training protocols, offering novel guidelines for skill development. By integrating force perturbations with time-dependent variables, Refaely’s research provides actionable insights for surgical education, potentially reducing training times and improving patient outcomes. Her work is particularly notable for its interdisciplinary approach, merging robotics, machine learning, and cognitive science to solve real-world clinical challenges.
Research Focus
Key Achievements
Top Papers
- 1
- 2