jeya-maria-jose/On-The-Fly-Adaptation

Code base for "On-the-Fly Test-time Adaptation for Medical Image Segmentation"

27
/ 100
Experimental

This tool helps medical imaging professionals maintain the accuracy of deep learning models when analyzing new patient scans that might look different from the data the model was originally trained on. You input a new medical image, and it intelligently adapts the existing model on-the-fly to provide a more accurate segmentation (e.g., identifying organs or anomalies) for that single image, without needing to retrain the entire model. This is ideal for radiologists, clinicians, or researchers working with diverse medical image datasets.

No commits in the last 6 months.

Use this if you are performing medical image segmentation and need your models to perform reliably on new, unseen patient data distributions without extensive retraining or complex adaptation setups.

Not ideal if you are working with non-medical image data or if you need to perform full model retraining on new datasets rather than single-image adaptation.

medical-imaging image-segmentation radiology clinical-diagnosis biomedical-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 4 / 25

How are scores calculated?

Stars

31

Forks

1

Language

Python

License

MIT

Last pushed

Mar 10, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jeya-maria-jose/On-The-Fly-Adaptation"

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