Related Experiment Video
Updated: Aug 5, 2026
07:46
Automatic Surgery in Transcatheter Aortic Valve Replacement Using Augmented Reality
Published on: August 9, 2024
Cross-Stream and Cross-Channel Attention Networks for Surgical Skill Classification in Open Surgery From Hand
Constantinos Loukas1, Konstantina Prevezanou1, Ioannis Seimenis1
1Laboratory of Medical Physics, Medical School, National and Kapodistrian University of Athens, Athens, Greece.
Summary
This study introduces a deep learning model to assess surgical skill in open surgery (OS) using hand kinematics. The model effectively classifies skill levels, outperforming human reviewers in key metrics.
Area of Science:
- Surgical Skill Assessment
- Medical Technology
- Artificial Intelligence in Surgery
Background:
- Skill assessment in open surgery (OS) lags behind minimally invasive surgery research.
- Objective evaluation of OS skills is crucial for training and patient safety.
Purpose of the Study:
- To develop and evaluate deep learning models for automated surgical skill assessment in open surgery.
- To investigate the utility of hand kinematics for classifying surgical skill levels.
Main Methods:
- Trainees performed knot tying, continuous suturing, and interrupted suturing tasks (201 trials total).
- LSTM and Transformer-based deep learning models analyzed hand kinematics for skill classification.
- A novel architecture with attention mechanisms captured inter-hand, intra-hand, and stream-level motion interactions.
Main Results:
- The inter-hand deep learning model demonstrated superior performance across all tasks compared to an independent reviewer.
- The model achieved high accuracy in skill classification (e.g., 88% for knot tying, 84% for continuous suturing).
- Skill recognition varied by task complexity, with better high-skill recognition for knot tying and better low-skill recognition for suturing tasks.
Conclusions:
- Hand kinematic relationships are vital indicators for assessing surgical performance in open surgery.
- Deep learning models offer a promising approach for objective and reliable surgical skill evaluation.
- This technology can enhance surgical training and improve patient outcomes.