Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

rdme update #57

Merged
merged 3 commits into from
Feb 21, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
35 changes: 22 additions & 13 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -66,10 +66,31 @@ Please also cite the following original authors of the algorithms who make this
| scan-20 & scan_lite-20 | McKinley, R., Rebsamen, M., Dätwyler, K., Meier, R., Radojewski, P., & Wiest, R. (2021). Uncertainty-driven refinement of tumor-core segmentation using 3d-to-2d networks with label uncertainty. In Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries: 6th International Workshop, BrainLes 2020, (pp. 401-411). Springer International Publishing. |


## Usage
BrainLes features [Jupyter notebook tutorials](https://github.com/BrainLesion/tutorials/tree/main/BraTS-Toolkit) for glioma segmentation with BraTS Toolkit.
Further, have a look at the Python examples in this repository for preprocessing (`0_preprocessing_single.py`), segmentation (`1_segmentation.py`) and fusion (`2_fusion.py`).

## Brats Preprocessor
## Brats Segmentor
BraTS Segmentor enables orchestration of BraTS brain tumor segmentation algorithms for generation of fully-automated segmentations.
For segmentation your files should be `preprocessed`, meaning they should be co-registered and skullstripped in SRI-24 space.
You can preprocess your files using [BrainLes preprocessing](https://github.com/BrainLesion/preprocessing) (recommended) or the deprecated preprocessor of BraTS Toolkit (see below).

### Python package
Please have a look at `1_segmentation.py` in this repository for a demo application.

### Command Line Interface (CLI)
Type `brats-segment -h` after installing the python package to see available options.

## Brats Fusionator
BraTS Fusionator can combine the resulting candidate segmentations into consensus segmentations using fusion methods such as majority voting and iterative SIMPLE fusion.
### Python package
Please have a look at `2_fusion.py` in this repository for a demo application.

## Brats Preprocessor (deprecated)
BraTS Preprocessor facilitates data standardization and preprocessing for researchers and clinicians alike. It covers the entire image analysis workflow prior to tumor segmentation, from image conversion and registration to brain extraction.

> WARNING: BraTS Preprocessor is deprecated. It still works but we recommended using [BrainLes preprocessing](https://github.com/BrainLesion/preprocessing) instead which offers much more flexibility.

### Processing Modi
BraTS Preprocessor offers the following preprocessing modes:
#### GPU brain extraction: "gpu"
Expand Down Expand Up @@ -101,18 +122,6 @@ Type `brats-batch-preprocess -h` after installing the python package to see avai
You can find instructions to use and download the GUI variant here: https://neuronflow.github.io/BraTS-Preprocessor/
> WARNING: The GUI is not nicely maintained. We encourage you to use the python package or the CLI instead.

## Brats Segmentor
BraTS Segmentor enables orchestration of BraTS brain tumor segmentation algorithms for generation of fully-automated segmentations.
### Python package
Please have a look at `1_segmentation.py` in this repository for a demo application.

### Command Line Interface (CLI)
Type `brats-segment -h` after installing the python package to see available options.

## Brats Fusionator
BraTS Fusionator can combine the resulting candidate segmentations into consensus segmentations using fusion methods such as majority voting and iterative SIMPLE fusion.
### Python package
Please have a look at `2_fusion.py` in this repository for a demo application.

### Command Line Interface (CLI)
Type `brats-fuse -h` after installing the python package to see available options.
Expand Down
11 changes: 8 additions & 3 deletions brats_toolkit/util/citation_reminder.py
Original file line number Diff line number Diff line change
Expand Up @@ -27,17 +27,22 @@ def wrapper(*args, **kwargs):
console = Console()
console.rule("[bold red]Deprecation note[/bold red]")
console.print(
"Support for BraTS Toolkit's preprocessor will be deprecated soon, even though it should continue working.",
"Deprecation Notice: Support for the BraTS Toolkit's preprocessor is now deprecated, although it is expected to remain functional.",
justify="center",
)
console.print(
"You can already beta test the new BrainLes preprocessing: https://github.com/BrainLesion/preprocessing",
"Please note that this deprecation does not impact the segmentation and fusion module, which will continue to receive maintenance and support.",
justify="center",
)
console.print(
"Unlike the original preprocessing from BraTS Toolkit, the new pipeline allows for arbitrary sequences, implements multiple backends for registration and brain extration and does not require docker.",
"We recommend transitioning to the BrainLes preprocessing tool available at: https://github.com/BrainLesion/preprocessing for preprocessing tasks.",
justify="center",
)
console.print(
"In contrast to the original BraTS Toolkit preprocessing, the new BrainLes pipeline offers the flexibility of arbitrary sequences, incorporates multiple backends for registration and brain extraction, and eliminates the need for Docker.",
justify="center",
)

console.rule()
console.line()
func(*args, **kwargs)
Expand Down
Loading