STITCH 2.0: Extending Augmented Suturing with EKF Needle Estimation and Thread Management

2025-10-29

AI Summary

Surgical suture precision critically influences wound healing quality and scar formation; however, manual suturing suffers from high inter-operator variability, while existing robotic systems (e.g., STITCH 1.0) face fundamental limitations—including inaccurate needle pose estimation, suture thread tangling, and poor 3D alignment—preventing full wound closure. To address these challenges, we introduce seven key technical advancements: (1) real-time, high-accuracy needle pose estimation via fused extended Kalman filtering (EKF); (2) thread state recognition and active untangling; (3) automated 3D suture path alignment; and (4) integrated vision-based servoing with dynamic path planning. Experimental results demonstrate an average of 4.87 stitches per cycle, a 74.4% wound closure rate, a 66% increase in suture count, and a 38% reduction in execution time versus prior systems. With at most two human interventions, 100% closure is achieved—substantially enhancing the reliability and clinical feasibility of fully autonomous continuous suturing.

Technology Category

• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Computer Vision: Vision for Robotics & Autonomous Driving

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Surgical suturing is a high-precision task that impacts patient healing and scarring. Suturing skill varies widely between surgeons, highlighting the need for robot assistance. Previous robot suturing works, such as STITCH 1.0 [1], struggle to fully close wounds due to inaccurate needle tracking and poor thread management. To address these challenges, we present STITCH 2.0, an elevated augmented dexterity pipeline with seven improvements including: improved EKF needle pose estimation, new thread untangling methods, and an automated 3D suture alignment algorithm. Experimental results over 15 trials find that STITCH 2.0 on average achieves 74.4% wound closure with 4.87 sutures per trial, representing 66% more sutures in 38% less time compared to the previous baseline. When two human interventions are allowed, STITCH 2.0 averages six sutures with 100% wound closure rate. Project website: https://stitch-2.github.io/

Problem

• Improves needle pose estimation for surgical robot suturing accuracy
• Enhances thread management to prevent tangling during automated suturing
• Increases wound closure rate through better 3D suture alignment

Innovation

• EKF needle pose estimation for tracking
• Thread untangling methods for management
• Automated 3D suture alignment algorithm