Kaminyou/Kernelized-Instance-Normalization

[ECCV 2022] Official implementation of "Ultra-high-resolution unpaired stain transformation via Kernelized Instance Normalization"

33
/ 100
Emerging

This project helps pathologists and medical researchers transform ultra-high-resolution images of stained tissue samples. You provide an image stained with one chemical (e.g., Hematoxylin and Eosin) and it outputs an image that appears to be stained with another (e.g., Estrogen Receptor), enabling new insights without needing to restain or acquire new samples. It's designed for professionals working with microscopic pathology slides.

No commits in the last 6 months.

Use this if you need to digitally convert a high-resolution microscopic image stained with one reagent to appear as if it were stained with a different reagent, without physically re-staining the sample.

Not ideal if you are looking for the absolute latest version of this technology, as the developers recommend a newer method, or if you are working with standard resolution images.

pathology histology medical-imaging stain-transformation digital-microscopy
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

37

Forks

4

Language

Python

License

MIT

Last pushed

Oct 12, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Kaminyou/Kernelized-Instance-Normalization"

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