BraTS

Providing the top performing algorithms from the Brain Tumor Segmentation (BraTS) challenges, through an easy to use Python API powered by docker.

Features

• Access to top-performing algorithms from recent BraTS challenges
• Easy-to-use minimal API
• Extensive documentation and examples

Installation

With a Python 3.8+ environment, you can install brats directly from PyPI:

pip install brats

Important

To run brats you require a Docker installation.
Many algorithms also require GPU support (NVIDIA Docker).
In case you do not have access to a Cuda-capable GPU, the overview tables in the Available Algorithms and Usage section indicate which algorithms are CPU compatible.

Docker and NVIDIA Container Toolkit Setup

• Docker: Installation instructions on the official website
• NVIDIA Container Toolkit: Refer to the NVIDIA install guide and the official GitHub page

Available Algorithms and Usage

Segmentation

Adult Glioma Segmentation (Pre Treatment)

from brats import AdultGliomaPreTreatmentSegmenter
from brats.constants import AdultGliomaPreTreatmentAlgorithms

segmenter = AdultGliomaPreTreatmentSegmenter(algorithm=AdultGliomaPreTreatmentAlgorithms.BraTS23_1, cuda_devices="0")
# these parameters are optional, by default the winning algorithm of 2023 will be used on cuda:0
segmenter.infer_single(
    t1c="path/to/t1c.nii.gz",
    t1n="path/to/t1n.nii.gz",
    t2f="path/to/t2f.nii.gz",
    t2w="path/to/t2w.nii.gz",
    output_file="segmentation.nii.gz",
)

Class: brats.AdultGliomaPreTreatmentSegmenter (Docs)

Year	Rank	Author	Paper	CPU Support	Key Enum
2023	1st	André Ferreira, et al.	Link	❌	BraTS23_1
2023	2nd	Andriy Myronenko, et al.	N/A	❌	BraTS23_2
2023	3rd	Fadillah Adamsyah Maani, et al.	N/A	❌	BraTS23_3

Adult Glioma Segmentation Post Treatment

from brats import AdultGliomaPostTreatmentSegmenter
from brats.constants import AdultGliomaPostTreatmentAlgorithms

segmenter = AdultGliomaPostTreatmentSegmenter(algorithm=AdultGliomaPostTreatmentAlgorithms.BraTS23_1, cuda_devices="0")
# these parameters are optional, by default the winning algorithm of 2024 will be used on cuda:0
segmenter.infer_single(
    t1c="path/to/t1c.nii.gz",
    t1n="path/to/t1n.nii.gz",
    t2f="path/to/t2f.nii.gz",
    t2w="path/to/t2w.nii.gz",
    output_file="segmentation.nii.gz",
)

Class: brats.AdultGliomaPostTreatmentSegmenter (Docs)

Year	Rank	Author	Paper	CPU Support	Key Enum
2024	1st	André Ferreira, et al.	N/A	❌	BraTS24_1
2024	2nd	Team kimbab	N/A	❌	BraTS24_2
2024	3rd	Adrian Celaya	N/A	✅	BraTS24_3

BraTS-Africa Segmentation

from brats import AfricaSegmenter
from brats.constants import AfricaAlgorithms

segmenter = AfricaSegmenter(algorithm=AfricaAlgorithms.BraTS23_1, cuda_devices="0")
# these parameters are optional, by default the winning algorithm will be used on cuda:0
segmenter.infer_single(
    t1c="path/to/t1c.nii.gz",
    t1n="path/to/t1n.nii.gz",
    t2f="path/to/t2f.nii.gz",
    t2w="path/to/t2w.nii.gz",
    output_file="segmentation.nii.gz",
)

Class: brats.AfricaSegmenter (Docs)

Year	Rank	Author	Paper	CPU Support	Key Enum
2024	1st	Zhifan Jiang et al.	N/A	❌	BraTS24_1
2024	2nd	Long Bai, et al.	N/A	✅	BraTS24_2
2024	1st	Sarim Hashmi, et al.	N/A	❌	BraTS24_3
2023	1st	Andriy Myronenko, et al.	TODO	❌	BraTS23_1
2023	2nd	Alyssa R Amod, et al.	N/A	❌	BraTS23_2
2023	3rd	Ziyan Huang, et al.	N/A	✅	BraTS23_3

Meningioma Segmentation

Note
Unlike other segmentation challenges the expected inputs for the Meningioma Segmentation Algorithms differ between years.

• 2023: All 4 modalities are used (t1c, t1n, t2f, t2w)
• 2024: Only t1c is used

Therefore the usage differs slightly, depending on which algorithm is used. To understand why, please refer to the 2024 challenge manuscript.

from brats import MeningiomaSegmenter
from brats.constants import MeningiomaAlgorithms

### Example for 2023 algorithms
segmenter = MeningiomaSegmenter(algorithm=MeningiomaAlgorithms.BraTS23_1, cuda_devices="0")
# these parameters are optional, by default the winning algorithm will be used on cuda:0
segmenter.infer_single(
    t1c="path/to/t1c.nii.gz",
    t1n="path/to/t1n.nii.gz",
    t2f="path/to/t2f.nii.gz",
    t2w="path/to/t2w.nii.gz",
    output_file="segmentation_23.nii.gz",
)

### Example for 2024 algorithms
segmenter = MeningiomaSegmenter(algorithm=MeningiomaAlgorithms.BraTS24_1, cuda_devices="0")
segmenter.infer_single(
    t1c="path/to/t1c.nii.gz",
    output_file="segmentation_24.nii.gz",
)

Class: brats.MeningiomaSegmenter (Docs)

Year	Rank	Author	Paper	CPU Support	Key Enum
2024	1st	Valeria Abramova	N/A	❌	BraTS24_1
2024	2nd	Mehdi Astaraki	N/A	❌	BraTS24_2
2024	3rd	Andre Ferreira, et al.	N/A	✅	BraTS24_3
2023	1st	Andriy Myronenko, et al.	N/A	❌	BraTS23_1
2023	2nd	Ziyan Huang, et al.	N/A	✅	BraTS23_2
2023	3rd	Zhifan Jiang et al.	N/A	❌	BraTS23_3

Brain Metastases Segmentation

from brats import MetastasesSegmenter
from brats.constants import MetastasesAlgorithms

segmenter = MetastasesSegmenter(algorithm=MetastasesAlgorithms.BraTS23_1, cuda_devices="0")
# these parameters are optional, by default the winning algorithm will be used on cuda:0
segmenter.infer_single(
    t1c="path/to/t1c.nii.gz",
    t1n="path/to/t1n.nii.gz",
    t2f="path/to/t2f.nii.gz",
    t2w="path/to/t2w.nii.gz",
    output_file="segmentation.nii.gz",
)

Class: brats.MetastasesSegmenter (Docs)

Year	Rank	Author	Paper	CPU Support	Key Enum
2023	1st	Andriy Myronenko, et al.	N/A	❌	BraTS23_1
2023	2nd	Siwei Yang, et al.	N/A	❌	BraTS23_2
2023	3rd	Ziyan Huang, et al.	N/A	✅	BraTS23_3

Pediatric Segmentation

from brats import PediatricSegmenter
from brats.constants import PediatricAlgorithms

segmenter = PediatricSegmenter(algorithm=PediatricAlgorithms.BraTS23_1, cuda_devices="0")
# these parameters are optional, by default the winning algorithm will be used on cuda:0
segmenter.infer_single(
    t1c="path/to/t1c.nii.gz",
    t1n="path/to/t1n.nii.gz",
    t2f="path/to/t2f.nii.gz",
    t2w="path/to/t2w.nii.gz",
    output_file="segmentation.nii.gz",
)

Class: brats.PediatricSegmenter (Docs)

Year	Rank	Author	Paper	CPU Support	Key Enum
2024	1st	Tim Mulvany, et al.	N/A	❌	BraTS24_1
2024	2nd	Mehdi Astaraki	N/A	❌	BraTS24_2
2024	3rd	Sarim Hashmi, et al.	N/A	❌	BraTS24_3
2023	1st	Zhifan Jiang et al.	N/A	❌	BraTS23_1
2023	2nd	Andriy Myronenko, et al.	N/A	❌	BraTS23_2
2023	3rd	Yubo Zhou	N/A	❌	BraTS23_3

Generalizability Across Tumors (BraTS-GoAT) Segmentation

from brats import GoATSegmenter
from brats.constants import GoATAlgorithms

segmenter = GoATSegmenter(algorithm=GoATAlgorithms.BraTS24_1, cuda_devices="0")
# these parameters are optional, by default the winning algorithm will be used on cuda:0
segmenter.infer_single(
    t1c="path/to/t1c.nii.gz",
    t1n="path/to/t1n.nii.gz",
    t2f="path/to/t2f.nii.gz",
    t2w="path/to/t2w.nii.gz",
    output_file="segmentation.nii.gz",
)

Class: brats.PediatricSegmenter (Docs)

Year	Rank	Author	Paper	CPU Support	Key Enum
2024	1st	Frank Miao, Shengjie Niu	N/A	❌	BraTS24_1

Inpainting

Inpainting

from brats import Inpainter
from brats.constants import InpaintingAlgorithms

inpainter = Inpainter(algorithm=InpaintingAlgorithms.BraTS24_1, cuda_devices="0")
inpainter.infer_single(
    t1n="path/to/voided_t1n.nii.gz",
    mask="path/to/mask.nii.gz",
    output_file="inpainting.nii.gz",
)

Class: brats.Inpainter (Docs)

Year	Rank	Author	Paper	CPU Support	Key Enum
2024	1st	Ke Chen, Juexin Zhang, Ying Weng	N/A	✅	BraTS24_1
2024	2nd	André Ferreira, et al.	N/A	❌	BraTS24_2
2024	3rd	Team SMINT	N/A	❌	BraTS24_3
2023	1st	Juexin Zhang, et al.	N/A	✅	BraTS23_1
2023	2nd	Alicia Durrer, et al.	N/A	❌	BraTS23_2
2023	3rd	Jiayu Huo, et al.	N/A	✅	BraTS23_3

Missing MRI

Missing MRI

from brats import MissingMRI
from brats.constants import MissingMRIAlgorithms

missing_mri = MissingMRI(algorithm=MissingMRIAlgorithms.BraTS24_1, cuda_devices="0")
# Example to synthesize t2f modality (whichever modality is missing will be inferred)
missing_mri.infer_single(
    t1c="path/to/t1c.nii.gz",
    t1n="path/to/t1n.nii.gz",
    # t2f="path/to/t2f.nii.gz",
    t2w="path/to/t2w.nii.gz",
    output_file="inferred_t2f.nii.gz",
)

Class: brats.MissingMRI (Docs)

Year	Rank	Author	Paper	CPU Support	Key Enum
2024	1st	Jihoon Cho, Seunghyuck Park, Jinah Park	N/A	❌	BraTS24_1
2024	2nd	Haowen Pang	N/A	❌	BraTS24_2
2024	3rd	Minjoo Lim, Bogyeong Kang	N/A	❌	BraTS24_3

---

Tip

For a full notebook example with more details please check here:

Citation

If you use BraTS in your research, please cite it to support the development!

TODO: citation will be added asap

Contributing

We welcome all kinds of contributions from the community!

Reporting Bugs, Feature Requests and Questions

Please open a new issue here.

Code contributions

Nice to have you on board! Please have a look at our CONTRIBUTING.md file.