Fengbei Liu

Australian Centre for Robotic Vision, University of Adelaide

Papers

Total Citations

H-Index

About

Fengbei Liu’s research lies at the intersection of computer vision, deep learning, and minimally invasive surgery, with a primary focus on advancing arthroscopic procedures through intelligent automation. His most cited work, “Automatic Segmentation of Multiple Structures in Knee Arthroscopy Using Deep Learning” (2020, 41 citations), pioneers the use of convolutional neural networks to automatically delineate anatomical structures in arthroscopic video, directly addressing the limited intra-operative visualization that surgeons face during minimally invasive surgery. This contribution enhances surgical precision and safety by providing real-time semantic guidance. Liu further extends this line of inquiry in “3D Semantic Mapping from Arthroscopy Using Out-of-Distribution Pose and Depth and In-Distribution Segmentation Training” (2021), where he tackles the challenge of building 3D scene understanding from monocular arthroscopic images, leveraging out-of-distribution pose estimation and depth learning alongside robust segmentation. Though early in citation impact, this work signals a forward-looking approach to creating comprehensive spatial maps of the surgical field. Liu’s research is notable for its translational potential—bridging state-of-the-art AI with practical surgical needs—and positions him as an emerging leader in computer-assisted orthopedics.