egeozsoy/4D-OR

Official code of the paper 4D-OR: Semantic Scene Graphs for OR Domain Modeling accepted at MICCAI 2022. This repo includes both the dataset and our code.

29
/ 100
Experimental

This project helps medical researchers and AI developers working on surgical assistance systems to better understand and model activities in operating rooms. It processes 4D video and depth data of surgical procedures, along with automatically detected human poses and object bounding boxes, to generate detailed semantic scene graphs. These graphs show the objects present, their locations, and the roles of the medical personnel involved.

No commits in the last 6 months.

Use this if you need a comprehensive dataset and computational framework to analyze and model complex surgical environments for applications like surgical phase recognition or robotic assistance.

Not ideal if you are looking for a ready-to-use application for real-time surgical guidance or a tool outside of surgical scene understanding.

surgical-AI operating-room-analytics medical-image-computing surgical-robotics human-pose-estimation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

63

Forks

2

Language

Python

License

MIT

Last pushed

Mar 29, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/egeozsoy/4D-OR"

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