What question did this study set out to answer?

June 4, 2026Scientific DataOpen Access

Multicenter fine annotated surgical video dataset for minimally invasive glaucoma surgery

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial develops a detailed surgical video dataset for glaucoma surgeries, suggesting enhanced training for surgical navigation systems.

The aim is to create a comprehensive video dataset for minimally invasive glaucoma surgery to support surgical navigation systems.
Developed a large-scale surgical video dataset from multiple centers with fine annotations.
Included millions of frames annotated with surgical instruments and anatomical structures.
Organized annotations into two tasks: phase recognition and semantic segmentation.
Created the first multicenter annotated dataset for MIGS including extensive annotations.
Task I successfully identifies different stages of surgery; Task II focuses on detailed segmentation of instruments.
Dataset serves as a crucial resource for training computer vision models.

Wang et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

Randomized trial develops a detailed surgical video dataset for glaucoma surgeries, suggesting enhanced training for surgical navigation systems.