Skip to content

Commit 5ccc187

Browse files
Merge branch 'andreped-fix/readme-update' into development
2 parents f9df314 + e156b99 commit 5ccc187

File tree

1 file changed

+21
-8
lines changed

1 file changed

+21
-8
lines changed

README.md

Lines changed: 21 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -5,14 +5,16 @@
55
[![Pip Downloads](https://img.shields.io/pypi/dm/torchstain?label=pip%20downloads&logo=python)](https://pypi.org/project/torchstain/)
66
[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.7692014.svg)](https://doi.org/10.5281/zenodo.7692014)
77

8-
GPU-accelerated stain normalization tools for histopathological images. Compatible with PyTorch, TensorFlow, and Numpy.
8+
GPU-accelerated stain tools for histopathological images. Compatible with PyTorch, TensorFlow, and Numpy.
9+
910
Normalization algorithms currently implemented:
11+
- Macenko [\[1\]](#reference) (ported from [numpy implementation](https://github.com/schaugf/HEnorm_python))
12+
- Reinhard [\[2\]](#reference)
13+
- Modified Reinhard [\[3\]](#reference)
14+
- Multi-target Macenko [\[4\]](#reference)
1015

11-
| Algorithm | numpy | torch | tensorflow |
12-
|-|-|-|-|
13-
| Macenko [\[1\]](#reference) | ✓ | ✓ | ✓ |
14-
| Reinhard [\[2\]](#reference) | ✓ | ✓ | ✓ |
15-
| Modified Reinhard [\[3\]](#reference) | ✓ | ✓ | ✓ |
16+
Augmentation algorithms currently implemented:
17+
- Macenko-Aug [\[1\]](#reference) (inspired by [StainTools](https://github.com/Peter554/StainTools))
1618

1719
## Installation
1820

@@ -47,9 +49,19 @@ norm, H, E = normalizer.normalize(I=t_to_transform, stains=True)
4749

4850
![alt text](data/result.png)
4951

52+
## Implemented algorithms
53+
54+
| Algorithm | numpy | torch | tensorflow |
55+
|-|-|-|-|
56+
| Macenko | ✓ | ✓ | ✓ |
57+
| Reinhard | ✓ | ✓ | ✓ |
58+
| Modified Reinhard | ✓ | ✓ | ✓ |
59+
| Multi-target Macenko | ✗ | ✓ | ✗ |
60+
| Macenko-Aug | ✓ | ✓ | ✓ |
61+
5062
## Backend comparison
5163

52-
Macenko runtime results using different backends with 10 runs per image size on a Intel(R) Core(TM) i5-8365U CPU @ 1.60GHz.
64+
Runtimes using the Macenko algorithm using different backends. Metrics were calculated from 10 repeated runs for each quadratic image size on an Intel(R) Core(TM) i5-8365U CPU @ 1.60GHz.
5365

5466
| size | numpy avg. time | torch avg. time | tf avg. time |
5567
|--------|-------------------|-------------------|------------------|
@@ -66,7 +78,8 @@ Macenko runtime results using different backends with 10 runs per image size on
6678

6779
- [1] Macenko, Marc et al. "A method for normalizing histology slides for quantitative analysis." 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro. IEEE, 2009.
6880
- [2] Reinhard, Erik et al. "Color transfer between images." IEEE Computer Graphics and Applications. IEEE, 2001.
69-
- [3] Roy, Santanu et al. "Modified Reinhard Algorithm for Color Normalization of Colorectal Cancer Histopathology Images". 2021 29th European Signal Processing Conference (EUSIPCO). IEEE, 2021.
81+
- [3] Roy, Santanu et al. "Modified Reinhard Algorithm for Color Normalization of Colorectal Cancer Histopathology Images". 2021 29th European Signal Processing Conference (EUSIPCO), IEEE, 2021.
82+
- [4] Ivanov, Desislav et al. "Multi-target stain normalization for histology slides". arXiv (preprint). 2024.
7083

7184
## Citing
7285

0 commit comments

Comments
 (0)