HumanSignal / HumanSignal/label-studio

Co-annotating across different image contrasts

Open
#6,137 1 comment 0 reactions 0 assignees View on GitHub
community:feature-request community:reviewed feature
Dominant language
TypeScript
Stars
28.3k
Forks
3.7k
Avg merge
14h
Merged PRs (30d)
15

Description

**Is your feature request related to a problem? Please describe.**
I often work with medical data which involves many different contrasts of the same heart. This means one annotation should be informed by multiple different contrasts, and it would be great to see a mask/keypoint annotation across all images simultaneously

**Describe the solution you'd like**
Say we have three images, which are all different "views" of the same image (DWI, MD, and Primary Eigenvalue). When I click pixel (50, 80), it would be great if the same point could show up at (50, 80) on all three other masks. This way, I could click/interchange between contrasts to annotate the final mask, and also see my mask on all three image contrasts to make sure my annotations fit all images.

**Describe alternatives you've considered**
We have our own annotation system in the lab but it's very RAM-consuming (difficult to use on an 8GB RAM laptop) and has high latency. We haven't found any other solutions, and this feature would be ver useful for all medical data.

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.