Yukan Wu

Papers

Total Citations

H-Index

About

Yukan Wu is a pioneering researcher in computational orthopedics and AI-assisted surgical planning, with a primary focus on developing deep learning algorithms for spinal procedures. His most notable contribution is the development and validation of a three-dimensional (3D) U-Net algorithm for automated pedicle screw planning in the thoracolumbosacral spine, a breakthrough that addresses one of the most technically demanding aspects of spinal surgery. In his landmark 2025 study, Wu trained his model on 1,235 retrospective cases, combining public datasets (CTSpine1K) with 230 clinical cases from Beijing Tongren Hospital, demonstrating the algorithm's feasibility in both research and real-world clinical settings. This work has already garnered 3 citations, reflecting its immediate relevance to the growing field of AI-driven surgical automation. Wu’s research bridges the critical gap between computational modeling and practical surgical application, offering the potential to reduce operative time, improve screw placement accuracy, and enhance patient safety. His approach exemplifies how deep learning can transform traditional surgical planning, making complex spinal procedures more accessible and reproducible. For students and researchers in biomedical engineering and neurosurgery, Wu’s work represents a compelling case study in translating AI innovations from bench to bedside.