Xingming Qu
Papers
2
Total Citations
18
H-Index
2
About
Xingming Qu is a researcher at the intersection of artificial intelligence and surgical education, with a primary focus on robotic-assisted surgery training and automated skill assessment. Their most significant contribution lies in pioneering the use of multi-task convolutional neural networks (CNNs) to objectively evaluate surgical performance from video recordings. In their landmark 2021 paper, "Evaluating robotic-assisted surgery training videos with multi-task convolutional neural networks," Qu demonstrated how deep learning can accurately assess robotic surgical skills, a breakthrough that has garnered 16 citations and promises to transform how surgeons are trained and credentialed. This work was further validated in their 2020 presentation at the Journal of Urology, where they showed that machine learning models can reliably differentiate levels of surgical expertise. By automating what was previously a subjective, time-intensive evaluation process, Qu’s research is helping to standardize surgical training, reduce bias in assessments, and ultimately improve patient outcomes. Their innovative application of multi-task learning—where a single model simultaneously evaluates multiple aspects of surgical performance—represents a significant step toward scalable, data-driven mentorship in robotic surgery.
Research Focus
Key Achievements
Top Papers
- 1
- 2