Peiran Wu

Papers

Total Citations

H-Index

About

Peiran Wu is a rising researcher in biomedical image analysis and computer-assisted surgery, with a focus on surgical instrument segmentation in challenging video environments. Their most-cited work, "Motion-Boundary-Driven Unsupervised Surgical Instrument Segmentation in Low-Quality Optical Flow" (2025), introduces a novel, unsupervised approach that leverages motion-boundary cues to segment surgical tools without the need for labeled training data—a significant breakthrough for real-time, low-quality video feeds common in minimally invasive procedures. This work, already garnering 2 citations shortly after publication, addresses a critical bottleneck in robotic surgery and intraoperative monitoring. Wu’s contributions lie at the intersection of optical flow analysis, unsupervised learning, and medical robotics, offering robust solutions where traditional supervised methods fail. Their research promises to enhance surgical autonomy and safety by enabling reliable instrument tracking in noisy, low-resolution streams. As an early-career scholar, Wu’s innovative use of motion-driven boundaries marks them as a promising voice in advancing computer vision for clinical applications, with potential for high-impact contributions to the future of smart operating rooms.