EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Using distilled knowledge from large transformer models for efficient identification of cataract surgery steps

John Xiang, Sophia Y. Wang

Frontiers in Digital Health · 19.11.2026 · 8

DOI: 10.3389/fdgth.2026.1869080 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Digital Health, online erschienen am 19.11.2026. Verfasst von John Xiang und 1 weiteren Autor:innen. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Eye Institute, Research to Prevent Blindness.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Automated analysis of cataract surgery videos can provide objective performance metrics for trainees and support consistent progress tracking. Large vision transformers perform well for medical image tasks, but their size can limit practical deployment.

Methods

We evaluated whether knowledge distillation can produce an efficient model for cataract surgical step recognition while preserving accuracy. We analyzed 268 resident cataract surgery videos collected across six sites and labeled with 14 surgical steps. A large teacher model pretrained with self-supervision was compared with a smaller student model trained using knowledge distillation, the same student trained without distillation, and a convolutional neural network baseline. Performance was assessed using overall accuracy and area under the receiver operating characteristic curve, and efficiency was assessed using parameter count and floating-point operations per frame.

Results

The distilled student achieved 87.7% accuracy and an area under the curve of 0.985, comparable to the teacher (87.7% accuracy; 0.970). The distilled student was substantially smaller (21.7 million vs. 85.8 million parameters) and more efficient (4.63 vs. 17.58 GFLOPs per frame). It also outperformed the student trained without distillation (85.5% accuracy; 0.963) and the best convolutional neural network baseline (85.6% accuracy; 0.973).

Discussion

These findings suggest that knowledge distillation can produce a lightweight, high-performing model for cataract surgical step recognition, reducing computational barriers relevant to deployment of automated feedback tools for surgical training.

Förderung

  • National Eye Institute
  • Research to Prevent Blindness

Zitieren

APA

Xiang, J., & Wang, S. Y. (2026). Using distilled knowledge from large transformer models for efficient identification of cataract surgery steps. Frontiers in Digital Health, 8. https://doi.org/10.3389/fdgth.2026.1869080

Vancouver

Xiang J, Wang SY. Using distilled knowledge from large transformer models for efficient identification of cataract surgery steps. Frontiers in Digital Health. 2026;8. doi:10.3389/fdgth.2026.1869080

BibTeX
@article{Xiang2026,
  author = {Xiang, John and Wang, Sophia Y.},
  title = {Using distilled knowledge from large transformer models for efficient identification of cataract surgery steps},
  journal = {Frontiers in Digital Health},
  year = {2026},
  volume = {8},
  doi = {10.3389/fdgth.2026.1869080}
}
Kostenlos starten →