ProtoFlow: interpretable and robust surgical workflow modeling with learned dynamic scene graph prototypes - Summary - MDSpire

ProtoFlow: interpretable and robust surgical workflow modeling with learned dynamic scene graph prototypes

  • By

  • Felix Holm

  • Ghazal Ghazaei

  • Nassir Navab

  • May 28, 2026

  • 0 min

Share

Objective:

To introduce ProtoFlow, a prototype learning framework for surgical workflow modeling that aims to enhance interpretability and generalizability using dynamic scene graphs.

Approach:
    Key Findings:
    • ProtoFlow outperforms existing baselines in surgical workflow recognition on the CAT-SG dataset.
    • The framework generalizes across different surgical procedures.
    Interpretation:

    Limitations:
    • The approach may still face challenges related to data scarcity and generalization across diverse surgical contexts.
    Conclusion:

    ProtoFlow provides a structured framework for surgical workflow modeling.

Original Source(s)

ProtoFlow: interpretable and robust surgical workflow modeling with learned dynamic scene graph prototypes

  • by Felix Holm, Ghazal Ghazaei, Nassir Navab

  • May 28, 2026

Related Content

ASC Growing Pains

Daniel Eisenstadt of Terramed Real Estate Solutions discusses factors that contribute to limited surgical capacity and what can be done about them.

  • May 1, 2026

  • 5 min
Effectiveness of Manuka Honey Eye Drops for Alleviating Dry Eye Symptoms Post-Cataract Surgery: A Prospective Controlled Trial

Success and Failure Rates with Increased-Range-of-Focus IOLs 

IRoF lenses offer high success, with some outperforming others