Peichao Li

Papers

Total Citations

H-Index

About

Peichao Li is a leading researcher at the intersection of robot-assisted surgery and artificial intelligence, with a primary focus on automated surgical skill assessment and medical image segmentation. His most impactful work introduces a cross-domain transfer learning framework for microsurgical skill evaluation, replacing subjective expert observation with objective, automated deep learning analysis of raw kinematic data—a paper that has garnered 52 citations and represents a significant step toward standardized surgical training. In medical imaging, Li developed the ACNN (full resolution DCNN), a novel architecture that avoids traditional down-sampling layers to preserve fine spatial details critical for 3D navigation in minimally invasive surgeries. This work, with 32 combined citations, addresses a fundamental limitation of conventional convolutional networks. He further advanced the field with Z-Net, an anisotropic 3D DCNN designed specifically for CT volume segmentation, enabling more accurate pre-operative planning and intra-operative guidance. Li’s contributions are shaping the future of autonomous surgical systems, providing the computational foundations for objective skill assessment and high-fidelity anatomical modeling that will ultimately improve patient outcomes and surgical training methodologies.