MLI-lab/Robustness-CS

Measuring the robustness of compressive sensing methods (including deep-learning-based ones) for image reconstruction.

36
/ 100
Emerging

This project helps medical imaging researchers and practitioners evaluate how robust image reconstruction methods are, especially those using deep learning. It takes partially acquired MRI data or existing reconstructions and produces quantitative measurements of how well different techniques recover details under various challenging conditions, like adversarial noise or shifts in data distribution. Medical imaging scientists and radiologists who develop or use advanced MRI reconstruction algorithms would benefit from this work.

No commits in the last 6 months.

Use this if you need to rigorously test the reliability and accuracy of image reconstruction algorithms, including deep learning models, for accelerated MRI under different types of perturbations and data variations.

Not ideal if you are looking for a tool to perform routine, robust image reconstruction without needing to analyze the underlying method's resilience to specific challenges.

medical-imaging MRI-reconstruction image-processing radiology data-robustness
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

32

Forks

5

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Jul 12, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/MLI-lab/Robustness-CS"

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