Autonomous laparoscope control improves surgical camera views during key phases
Semantic-Coupled Perception Framework for Autonomous Laparoscope Control
Robotics
Summary
Good camera views during minimally invasive surgery help doctors work safely and efficiently. The authors present a system that links understanding the surgery's current step with smart camera movement, so the camera keeps important things in view even when blocked or overlapping. Tests with data and practice setups show this method helps keep targets visible better than fixed cameras. This could make surgical cameras smarter and more helpful during operations.
What this means in practice
- •For surgical device manufacturers: Design laparoscopic camera systems that automatically adjust based on surgical phases to maintain better views despite occlusion or movement.$Commercial implications: Enables development of smarter surgical cameras improving focus and safety, creating new products for minimally invasive surgical equipment makers.
- •For medical robotics teams: Implement integrated phase recognition and visual tracking for autonomous laparoscope control to improve task-aware camera guidance during operations.
Authors
Enduo Zhao, Fangzhou Li, Yujie Zhu, Sicheng Lu, Fang Chen, Longfei Ma, Hongen Liao
Abstract
In minimally invasive surgery (MIS), maintaining an appropriate field of view (FoV) is essential for surgical safety and efficiency. However, conventional autonomous laparoscope control methods often treat visual tracking and surgical phase recognition independently, limiting robustness under occlusion, entity overlap, and camera motion. This paper proposes a closed-loop autonomous laparoscope control framework that couples real-time surgical phase recognition with camera-motion-compensated visual perception. By exploiting phase-dependent relationships among surgical entities, the framework improves target state estimation under challenging visual conditions, supporting task-aware autonomous FoV control. Experiments on benchmark datasets evaluate the proposed framework in surgical phase recognition and target tracking, including scenarios involving occlusion and entity overlap. Phantom experiments further demonstrate the feasibility of autonomous FoV control, showing improved target visibility and task execution performance compared with fixed-FoV control. These results highlight the potential of incorporating task-level semantics into visual state estimation for autonomous laparoscope guidance.