Papers
5
Total Citations
164
H-Index
4
About
Ruiqi Li is a researcher specializing in medical image analysis, computer vision, and robot-assisted minimally invasive surgery, with a particular focus on developing intelligent perception systems for surgical interventions. His most recognized contribution, RAUNet (Residual Attention U-Net), introduced an attention-guided deep learning architecture for the semantic segmentation of cataract surgical instruments, addressing challenging real-world problems such as specular reflection and class imbalance — work that has garnered over 150 citations and established him as a notable voice in surgical instrument segmentation. Building on this foundation, Li has extended his research into endovascular interventions, developing a real-time multi-task framework for guidewire segmentation and endpoint localization, as well as a multimodal fusion architecture for recognizing natural manipulation patterns in percutaneous coronary interventions. His more recent work includes a dual-stream approach for real-time aneurysm morphological analysis, tackling the persistent challenges of ambiguous anatomical boundaries in robotic surgery. Across his body of work, Li consistently bridges the gap between deep learning innovation and clinical applicability, making meaningful contributions toward safer, more autonomous surgical robotics systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5