Shota Kishi
Papers
1
Total Citations
2
H-Index
1
About
Shota Kishi’s research lies at the intersection of surgical robotics and computer vision, with a primary focus on enabling autonomous systems to understand and anticipate surgical workflows. His most cited work, “Convolutional Neural Network based on Temporal Pose Features for Surgical Procedure Recognition” (2021), directly addresses a critical bottleneck in operating room automation: the severe global shortage of scrub nurses. Kishi contributes to the development of a Scrub Nurse Robot (SNR) system by designing deep learning models that recognize surgical procedures from temporal pose features. This allows the robot to not only observe but also predict the sequence of actions in a surgery, moving beyond simple tool tracking toward genuine procedural understanding. While his citation count is still growing—reflecting the early-stage, high-impact nature of his work—Kishi’s research is foundational for creating intelligent robotic assistants that can seamlessly collaborate with human surgical teams. His approach, combining convolutional neural networks with spatiotemporal pose analysis, represents a promising step toward safer, more efficient operating rooms where robots proactively support surgeons rather than merely react to commands.
Research Focus
Key Achievements
Top Papers
- 1