Xiaolin Cheng

Papers

Total Citations

H-Index

About

Xiaolin Cheng is a leading researcher in computer vision for robot-assisted surgery, with a focus on real-time surgical instrument detection and tracking. Their work addresses critical challenges in robotic minimally invasive surgery (RMIS), where precise, high-speed visual feedback is essential for safe and effective procedures. Cheng’s most-cited paper, “Real‐time surgical instrument detection in robot‐assisted surgery using a convolutional neural network cascade” (2019, 53 citations), introduced a novel frame-by-frame detection method that overcomes the limitations of single-tool deep learning approaches, significantly improving both speed and accuracy. Building on this, their 2017 study (35 citations) developed a hybrid tracking method combining convolutional neural networks (CNNs) with line segment detectors and spatio-temporal context, enabling robust two-dimensional tool tracking in complex surgical scenes. These contributions have advanced the integration of AI into surgical robotics, enhancing automation and safety. Cheng’s work is widely cited by researchers in medical robotics and computer vision, reflecting its impact on real-time visual perception systems. Their achievements underscore a commitment to translating deep learning innovations into practical, life-saving surgical technologies.