cherise215/AdvBias

[MICCAI 2020 Oral] Realistic Adversarial Data Augmentation for MR Image Segmentation

27
/ 100
Experimental

This helps medical image analysts and researchers improve the accuracy of machine learning models used for segmenting anatomical structures in MR images. It takes raw or augmented MR images and synthetically adds realistic 'bias field' artifacts, which are common signal corruptions, to make models more robust. The primary users are researchers and practitioners developing or training AI for medical image analysis.

No commits in the last 6 months.

Use this if you are training a neural network for medical image segmentation and need to make your model more resilient to realistic signal inconsistencies often found in MRI scans.

Not ideal if you are looking for general pixel-wise adversarial attacks or generating entirely new synthetic medical images from scratch.

medical-imaging MRI-analysis image-segmentation deep-learning-in-medicine radiology-AI
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

16

Forks

1

Language

Jupyter Notebook

License

MIT

Last pushed

Jul 05, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/cherise215/AdvBias"

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