ProtoFlow: interpretable and robust surgical workflow modeling with learned dynamic scene graph prototypes - Takeaways - MDSpire
Coming Soon: Introducing MDSpire News. Learn more
Conexiant’s news site is now MDSpire News. Learn more

Dynamic Scene Graph Prototypes for Interpretable and Resilient Modeling of Surgical Workflows

  • By

  • Felix Holm

  • Ghazal Ghazaei

  • Nassir Navab

  • May 28, 2026

Share

  • 1

    ProtoFlow is a prototype learning framework designed for surgical workflow modeling using dynamic scene graphs.

  • 2

    The framework enhances interpretability and generalizability by identifying recurring structured representations of surgical interactions.

  • 3

    ProtoFlow integrates self-supervised and supervised learning, enabling effective few-shot learning in surgical video analysis.

  • 4

    Evaluation on the CAT-SG dataset demonstrates that ProtoFlow outperforms existing baselines in surgical workflow recognition.

  • 5

    The approach supports qualitative deviation analysis, providing interpretable insights into variations in surgical workflows.

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

"Landmark" Dataset Maps Anterior Segment Disease

Moorfields and UCL launch dataset aiming to accelerate research into anterior segment conditions

  • July 16, 2026

  • 2 min
Clobetasol Suspension Eases Cataract Inflammation

Phase 3 trials show clobetasol propionate ophthalmic suspension rapidly reduced inflammation and pain after cataract surgery

  • July 6, 2026

  • 3 min
Dropless Cataract Surgery: What is the fuss about?

As cataract surgery continues to evolve, the focus is shifting beyond the operating theatre to the weakest part of the patient pathway – postoperative drops