EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Cross‐Stream and Cross‐Channel Attention Networks for Surgical Skill Classification in Open Surgery From Hand Kinematics

Constantinos Loukas iD, Konstantina Prevezanou iD, Ioannis Seimenis iD, Stylianos Kykalos iD, Dimitrios Schizas iD

The International Journal of Medical Robotics and Computer Assisted Surgery · 2026

DOI: 10.1002/rcs.70215 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The International Journal of Medical Robotics and Computer Assisted Surgery, 2026. Verfasst von Constantinos Loukas und 4 weiteren Autor:innen. Beteiligte Einrichtung: Laboratory of Medical Physics, Medical School, National and Kapodistrian University of Athens, Athens, Greece. Hauptthemen laut MEDLINE: Hand, Clinical Competence. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Despite the extensive research on skill assessment in minimally invasive surgery, applications in open surgery (OS) remain limited.

Methods

Twenty trainees performed three OS tasks—knot tying (KT), continuous suturing (CS), and interrupted suturing (IS)—yielding 201 trials. Various deep learning models based on LSTM and Transformer were evaluated for binary skill classification using hand kinematics. The proposed architecture integrates cross‐stream and cross‐channel attention mechanisms to capture inter‐hand, intra‐hand, and stream‐level motion interactions. Agreement with an independent reviewer was also assessed.

Results

The inter‐hand model achieved the best performance across all tasks and outperformed the reviewer in multiple metrics (e.g., Accuracy: 0.88 vs. 0.86 KT; 0.84 vs. 0.83 CS; 0.81 vs. 0.68 IS). High‐skill recognition was better for KT, whereas low‐skill recognition was better for the more demanding tasks, CS and IS.

Conclusions

Our study highlights the importance of capturing hand kinematic relationships as key indicators of surgical performance.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

HandClinical CompetenceHumansBiomechanical PhenomenaSuture TechniquesLong Short Term MemoryDeep LearningMinimally Invasive Surgical ProceduresNeural Networks, ComputerAttention

Stichwörter der Autor:innen

artificial intelligenceattentiondeep learninghand kinematicssurgical skill assessment

Autor:innen und Institutionen

  • Laboratory of Medical Physics, Medical School, National and Kapodistrian University of Athens, Athens, Greece.
  • 1st Department of Surgery, Laikon General Hospital, Medical School, National and Kapodistrian University of Athens, Athens, Greece.

ORCID-Profile: Constantinos Loukas, Konstantina Prevezanou, Ioannis Seimenis, Stylianos Kykalos, Dimitrios Schizas

Zitieren

APA

Loukas, C., Prevezanou, K., Seimenis, I., Kykalos, S., & Schizas, D. (2026). Cross‐Stream and Cross‐Channel Attention Networks for Surgical Skill Classification in Open Surgery From Hand Kinematics. The International Journal of Medical Robotics and Computer Assisted Surgery. https://doi.org/10.1002/rcs.70215

Vancouver

Loukas C, Prevezanou K, Seimenis I, Kykalos S, Schizas D. Cross‐Stream and Cross‐Channel Attention Networks for Surgical Skill Classification in Open Surgery From Hand Kinematics. The International Journal of Medical Robotics and Computer Assisted Surgery. 2026. doi:10.1002/rcs.70215

BibTeX
@article{Loukas2026,
  author = {Loukas, Constantinos and Prevezanou, Konstantina and Seimenis, Ioannis and Kykalos, Stylianos and Schizas, Dimitrios},
  title = {Cross‐Stream and Cross‐Channel Attention Networks for Surgical Skill Classification in Open Surgery From Hand Kinematics},
  journal = {The International Journal of Medical Robotics and Computer Assisted Surgery},
  year = {2026},
  doi = {10.1002/rcs.70215}
}
Kostenlos starten →