CAMMA-public/SelfSupSurg

Official repository for "Dissecting Self-Supervised Learning Methods for Surgical Computer Vision"

45
/ 100
Emerging

This project provides pre-trained models and scripts for analyzing surgical videos to understand what's happening during an operation. It takes raw surgical video frames as input and can identify surgical phases (like 'dissection' or 'clipping'), detect the presence of specific tools, or recognize action triplets (e.g., 'grasper grasping tissue'). This is useful for surgeons, researchers, and medical educators who want to develop better automated systems for surgical training, assistance, or quality control.

No commits in the last 6 months.

Use this if you are a medical researcher or developer working with surgical video data and need to accurately identify surgical phases, detect tools, or recognize actions without extensive manual video annotation.

Not ideal if you are looking for a ready-to-use, deployable application for real-time surgical assistance, as this project focuses on research and development of underlying models.

surgical-video-analysis medical-imaging surgical-training operating-room-analytics computer-assisted-surgery
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

44

Forks

17

Language

Python

License

Last pushed

May 23, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/CAMMA-public/SelfSupSurg"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.