Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

WetCat: Enabling Automated Skill Assessment in Wet-Lab Cataract Surgery Videos

Negin Ghamsarian, Raphael Sznitman, Klaus Schoeffmann, Jens Kowal

TL;DR

WetCat provides the first dataset of wet-lab cataract surgery videos for automated skill assessment, addressing the gaps of real-surgery datasets and manual evaluation. It offers high-resolution videos with four-phase annotations and dense semantic segmentations aligned to clinical frameworks GRASIS and OSCAR, focusing on capsulorhexis and phacoemulsification. The paper benchmarks multiple phase-recognition and segmentation models, showing bidirectional recurrent architectures improve phase accuracy and that SAM-LoRA with limited prompts can robustly segment rhexis. By providing data, tools, and benchmarks, WetCat enables objective, scalable training and benchmarking for ophthalmic education.

Abstract

To meet the growing demand for systematic surgical training, wet-lab environments have become indispensable platforms for hands-on practice in ophthalmology. Yet, traditional wet-lab training depends heavily on manual performance evaluations, which are labor-intensive, time-consuming, and often subject to variability. Recent advances in computer vision offer promising avenues for automated skill assessment, enhancing both the efficiency and objectivity of surgical education. Despite notable progress in ophthalmic surgical datasets, existing resources predominantly focus on real surgeries or isolated tasks, falling short of supporting comprehensive skill evaluation in controlled wet-lab settings. To address these limitations, we introduce WetCat, the first dataset of wet-lab cataract surgery videos specifically curated for automated skill assessment. WetCat comprises high-resolution recordings of surgeries performed by trainees on artificial eyes, featuring comprehensive phase annotations and semantic segmentations of key anatomical structures. These annotations are meticulously designed to facilitate skill assessment during the critical capsulorhexis and phacoemulsification phases, adhering to standardized surgical skill assessment frameworks. By focusing on these essential phases, WetCat enables the development of interpretable, AI-driven evaluation tools aligned with established clinical metrics. This dataset lays a strong foundation for advancing objective, scalable surgical education and sets a new benchmark for automated workflow analysis and skill assessment in ophthalmology training. The dataset and annotations are publicly available in Synapse.

WetCat: Enabling Automated Skill Assessment in Wet-Lab Cataract Surgery Videos

TL;DR

WetCat provides the first dataset of wet-lab cataract surgery videos for automated skill assessment, addressing the gaps of real-surgery datasets and manual evaluation. It offers high-resolution videos with four-phase annotations and dense semantic segmentations aligned to clinical frameworks GRASIS and OSCAR, focusing on capsulorhexis and phacoemulsification. The paper benchmarks multiple phase-recognition and segmentation models, showing bidirectional recurrent architectures improve phase accuracy and that SAM-LoRA with limited prompts can robustly segment rhexis. By providing data, tools, and benchmarks, WetCat enables objective, scalable training and benchmarking for ophthalmic education.

Abstract

To meet the growing demand for systematic surgical training, wet-lab environments have become indispensable platforms for hands-on practice in ophthalmology. Yet, traditional wet-lab training depends heavily on manual performance evaluations, which are labor-intensive, time-consuming, and often subject to variability. Recent advances in computer vision offer promising avenues for automated skill assessment, enhancing both the efficiency and objectivity of surgical education. Despite notable progress in ophthalmic surgical datasets, existing resources predominantly focus on real surgeries or isolated tasks, falling short of supporting comprehensive skill evaluation in controlled wet-lab settings. To address these limitations, we introduce WetCat, the first dataset of wet-lab cataract surgery videos specifically curated for automated skill assessment. WetCat comprises high-resolution recordings of surgeries performed by trainees on artificial eyes, featuring comprehensive phase annotations and semantic segmentations of key anatomical structures. These annotations are meticulously designed to facilitate skill assessment during the critical capsulorhexis and phacoemulsification phases, adhering to standardized surgical skill assessment frameworks. By focusing on these essential phases, WetCat enables the development of interpretable, AI-driven evaluation tools aligned with established clinical metrics. This dataset lays a strong foundation for advancing objective, scalable surgical education and sets a new benchmark for automated workflow analysis and skill assessment in ophthalmology training. The dataset and annotations are publicly available in Synapse.

Paper Structure

This paper contains 12 sections, 1 equation, 6 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Methods
  3. Capsulorhexis Assessment Metrics
  4. Phacoemulsification Assessment Metrics
  5. Dataset
  6. Usage Notes
  7. Technical Validation
  8. Experimental Settings for Phase Recognition
  9. Experimental Settings for Semantic Segmentation
  10. Training Settings
  11. Experimental Results
  12. Conclusion

Figures (6)

  • Figure 1: Hands-on cataract surgery training in the wet lab.
  • Figure 2: Overall framework for skill assessment in wetlab cataract surgery.
  • Figure 3: Distribution of surgical phase durations across videos and overall phase proportions in the dataset.
  • Figure 4: Comparison of segmentation label visibility and pixel distribution across videos.
  • Figure 5: Sample frames from relevant phases in a wet-lab cataract surgery.
  • ...and 1 more figures