3 feature add brats africa segmentation algorithms

README.md

@@ -25,12 +25,12 @@ pip install brats
 ### Docker and NVIDIA Container Toolkit Setup
 
 To run `brats` you need a working Docker installation.
-Most algorithms also require GPU support (NVIDIA Docker). 
+Most algorithms also require GPU support (NVIDIA Docker).
 
 Installation instructions:
-- **Docker**: Installation instructions on the official [website](https://docs.docker.com/get-docker/)
-- **NVIDIA Container Toolkit**: Refer to the [NVIDIA install guide](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html) and the official [GitHub page](https://github.com/NVIDIA/nvidia-container-toolkit) 
 
+- **Docker**: Installation instructions on the official [website](https://docs.docker.com/get-docker/)
+- **NVIDIA Container Toolkit**: Refer to the [NVIDIA install guide](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html) and the official [GitHub page](https://github.com/NVIDIA/nvidia-container-toolkit)
 
 ## Use Cases and Tutorials
 
@@ -51,32 +51,72 @@ segmenter.infer_single(
 For more examples and details please refer to our extensive Notebook tutorials [**TODO**]
 
 ## Algorithms
-| Challenge | Year | Position | Authors | Paper | CPU support |
-|---|---|---|---|---|---|
-| *Meningioma Segmentation* | 2023 | 1st | Andriy Myronenko, et al. | N/A | :heavy_multiplication_x: |
-|     | 2023 | 2nd | Ziyan Huang | N/A | :white_check_mark: |
-|     | 2023 | 3rd | Zhifan Jiang et al. | N/A | :heavy_multiplication_x: |
-| *Pediatric Segmentation* | 2023 | 1st | Zhifan Jiang et al. | N/A | :heavy_multiplication_x: |
-|     | 2023 | 2nd | Andriy Myronenko, et al. | N/A | :heavy_multiplication_x: |
-|     | 2023 | 3rd | Yubo Zhou | N/A | :heavy_multiplication_x: |
-| *Adult Glioma Segmentation* | 2023 | 1st | André Ferreira, et al. | [Link](https://arxiv.org/abs/2402.17317v1) | :heavy_multiplication_x: |
-|     | 2023 | 2nd | Andriy Myronenko, et al. | N/A | :heavy_multiplication_x: |
-|     | 2023 | 3rd | Fadillah Adamsyah Maani, et al. | N/A | :heavy_multiplication_x: |
+
+<details open>
+
+<summary> <strong> Adult Glioma Segmentation </strong> </summary>
+<br>
+
+| Year | Rank | Author                            | Paper                                      | CPU Support |
+| ---- | ---- | --------------------------------- | ------------------------------------------ | ----------- |
+| 2023 | 1st  | _André Ferreira, et al._          | [Link](https://arxiv.org/abs/2402.17317v1) | &#x274C;    |
+| 2023 | 2nd  | _Andriy Myronenko, et al._        | N/A                                        | &#x274C;    |
+| 2023 | 3rd  | _Fadillah Adamsyah Maani, et al._ | N/A                                        | &#x274C;    |
+
+</details>
+
+<details>
+<summary> <strong> BraTS-Africa Segmentation </strong> </summary>
+<br>
+
+| Year | Rank | Author                     | Paper | CPU Support |
+| ---- | ---- | -------------------------- | ----- | ----------- |
+| 2023 | 1st  | _Andriy Myronenko, et al._ | N/A   | &#x274C;    |
+| 2023 | 2nd  | _Alyssa R Amod, et al._    | N/A   | &#x274C;    |
+| 2023 | 3rd  | _Ziyan Huang, et al._      | N/A   | &#x2705;    |
+
+</details>
+
+<details>
+<summary> <strong> Meningioma Segmentation </strong> </summary>
+<br>
+
+| Year | Rank | Author                     | Paper | CPU Support |
+| ---- | ---- | -------------------------- | ----- | ----------- |
+| 2023 | 1st  | _Andriy Myronenko, et al._ | N/A   | &#x274C;    |
+| 2023 | 2nd  | _Ziyan Huang_              | N/A   | &#x2705;    |
+| 2023 | 3rd  | _Zhifan Jiang et al._      | N/A   | &#x274C;    |
+
+</details>
+
+<details>
+<summary> <strong> Pediatric Segmentation </strong> </summary>
+<br>
+
+| Year | Rank | Author                     | Paper | CPU Support |
+| ---- | ---- | -------------------------- | ----- | ----------- |
+| 2023 | 1st  | _Zhifan Jiang et al._      | N/A   | &#x274C;    |
+| 2023 | 2nd  | _Andriy Myronenko, et al._ | N/A   | &#x274C;    |
+| 2023 | 3rd  | _Yubo Zhou_                | N/A   | &#x274C;    |
+
+</details>
 
 ## 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](https://github.com/BrainLesion/BraTS/issues).
 
 ### Code contributions
+
 Nice to have you on board! Please have a look at our [CONTRIBUTING.md](CONTRIBUTING.md) file.

brats/__init__.py

@@ -2,4 +2,5 @@
     AdultGliomaSegmenter,
     MeningiomaSegmenter,
     PediatricSegmenter,
+    AfricaSegmenter,
 )

brats/algorithm_config.py

@@ -17,6 +17,10 @@ class MetaData:
     """If available, a url to the paper of the algorithm"""
     challenge: str
     """The challenge the algorithm was submitted to"""
+    rank: str
+    """The rank of the algorithm in the challenge"""
+    year: int
+    """The year the algorithm was submitted"""
 
 
 @dataclass

brats/algorithms.py

@@ -11,10 +11,12 @@
 from brats.algorithm_config import load_algorithms
 from brats.constants import (
     ADULT_GLIOMA_SEGMENTATION_ALGORITHMS,
+    AFRICA_SEGMENTATION_ALGORITHMS,
     MENINGIOMA_SEGMENTATION_ALGORITHMS,
     PEDIATRIC_SEGMENTATION_ALGORITHMS,
     AdultGliomaAlgorithms,
     Algorithms,
+    AfricaAlgorithms,
     MeningiomaAlgorithms,
     PediatricAlgorithms,
 )
@@ -56,7 +58,7 @@ def __init__(
     def _log_algorithm_info(self):
         """Log information about the selected algorithm."""
         logger.opt(colors=True).info(
-            f"Running algorithm: <light-green>{self.algorithm.meta.challenge}</>"
+            f"Running algorithm: <light-green>{self.algorithm.meta.challenge} [{self.algorithm.meta.rank} place]</>"
         )
         logger.opt(colors=True).info(
             f"<blue>(Paper)</> Consider citing the corresponding paper: {self.algorithm.meta.paper} by {self.algorithm.meta.authors}"
@@ -80,6 +82,24 @@ def _add_log_file_handler(self, log_file: Path | str) -> int:
 
         return logger_id
 
+    def _cleanup(
+        self, temp_data_folder: Path, temp_output_folder: Path, logger_id: Optional[int]
+    ) -> None:
+        try:
+            shutil.rmtree(temp_data_folder)
+        except PermissionError as e:
+            logger.warning(
+                f"Failed to remove temporary folder {temp_data_folder}. This is most likely caused by bad permission management of the docker container. \nError: {e}"
+            )
+        try:
+            shutil.rmtree(temp_output_folder)
+        except PermissionError as e:
+            logger.warning(
+                f"Failed to remove temporary folder {temp_output_folder}. This is most likely caused by bad permission management of the docker container. \nError: {e}"
+            )
+        if logger_id is not None:
+            logger.remove(logger_id)
+
     def infer_single(
         self,
         t1c: Path | str,
@@ -137,10 +157,11 @@ def infer_single(
             logger.info(f"Saved segmentation to: {output_file.absolute()}")
 
         finally:
-            shutil.rmtree(temp_data_folder)
-            shutil.rmtree(temp_output_folder)
-            if log_file is not None:
-                logger.remove(logger_id)
+            self._cleanup(
+                temp_data_folder=temp_data_folder,
+                temp_output_folder=temp_output_folder,
+                logger_id=logger_id if log_file else None,
+            )
 
     def infer_batch(
         self,
@@ -207,10 +228,11 @@ def infer_batch(
 
             logger.info(f"Saved results to: {output_folder.absolute()}")
         finally:
-            shutil.rmtree(temp_data_folder)
-            shutil.rmtree(temp_output_folder)
-            if log_file:
-                logger.remove(logger_id)
+            self._cleanup(
+                temp_data_folder=temp_data_folder,
+                temp_output_folder=temp_output_folder,
+                logger_id=logger_id if log_file else None,
+            )
 
 
 class AdultGliomaSegmenter(BraTSAlgorithm):
@@ -240,7 +262,7 @@ class MeningiomaSegmenter(BraTSAlgorithm):
     """Provides algorithms to perform tumor segmentation on adult meningioma MRI data.
 
     Args:
-        algorithm (AdultGliomaAlgorithms, optional): Select an algorithm. Defaults to MeningiomaAlgorithms.BraTS23_1.
+        algorithm (MeningiomaAlgorithms, optional): Select an algorithm. Defaults to MeningiomaAlgorithms.BraTS23_1.
         cuda_devices (Optional[str], optional): Which cuda devices to use. Defaults to "0".
         force_cpu (bool, optional): Execution will default to GPU, this flag allows forced CPU execution if the algorithm is compatible. Defaults to False.
     """
@@ -263,7 +285,7 @@ class PediatricSegmenter(BraTSAlgorithm):
     """Provides algorithms to perform tumor segmentation on pediatric MRI data
 
     Args:
-        algorithm (AdultGliomaAlgorithms, optional): Select an algorithm. Defaults to PediatricAlgorithms.BraTS23_1.
+        algorithm (PediatricAlgorithms, optional): Select an algorithm. Defaults to PediatricAlgorithms.BraTS23_1.
         cuda_devices (Optional[str], optional): Which cuda devices to use. Defaults to "0".
         force_cpu (bool, optional): Execution will default to GPU, this flag allows forced CPU execution if the algorithm is compatible. Defaults to False.
     """
@@ -280,3 +302,26 @@ def __init__(
             cuda_devices=cuda_devices,
             force_cpu=force_cpu,
         )
+
+
+class AfricaSegmenter(BraTSAlgorithm):
+    """Provides algorithms to perform tumor segmentation on data from the BraTSAfrica challenge
+
+    Args:
+        algorithm (AfricaAlgorithms, optional): Select an algorithm. Defaults to AfricaAlgorithms.BraTS23_1.
+        cuda_devices (Optional[str], optional): Which cuda devices to use. Defaults to "0".
+        force_cpu (bool, optional): Execution will default to GPU, this flag allows forced CPU execution if the algorithm is compatible. Defaults to False.
+    """
+
+    def __init__(
+        self,
+        algorithm: AfricaAlgorithms = AfricaAlgorithms.BraTS23_1,
+        cuda_devices: Optional[str] = "0",
+        force_cpu: bool = False,
+    ):
+        super().__init__(
+            algorithm=algorithm,
+            algorithms_file_path=AFRICA_SEGMENTATION_ALGORITHMS,
+            cuda_devices=cuda_devices,
+            force_cpu=force_cpu,
+        )

brats/algorithms/adult_glioma.yml

@@ -4,7 +4,9 @@ algorithms:
     meta:
       authors: André Ferreira, et al.
       paper: https://arxiv.org/abs/2402.17317v1
-      challenge: BraTS23 Adult Glioma Segmentation (1st place)
+      challenge: BraTS23 Adult Glioma Segmentation
+      rank: 1st
+      year: 2023
     run_args:
       docker_image: brainles/brats23_faking_it:latest
       input_name_schema: "BraTS-GLI-{id:05d}-000"
@@ -16,7 +18,9 @@ algorithms:
     meta:
       authors: Andriy Myronenko, et al.
       paper: N/A
-      challenge: BraTS23 Adult Glioma Segmentation (2nd place)
+      challenge: BraTS23 Adult Glioma Segmentation
+      rank: 2nd
+      year: 2023
     run_args:
       docker_image: brainles/brats23_nvauto:latest
       input_name_schema: "BraTS-GLI-{id:05d}-000"
@@ -28,7 +32,9 @@ algorithms:
     meta:
       authors: Fadillah Adamsyah Maani, et al.
       paper: N/A
-      challenge: BraTS23 Adult Glioma Segmentation (3rd place)
+      challenge: BraTS23 Adult Glioma Segmentation
+      rank: 3rd
+      year: 2023
     run_args:
       docker_image: brainles/brats23_biomedmbz:latest
       input_name_schema: "BraTS-GLI-{id:05d}-000"

brats/algorithms/africa.yml

@@ -0,0 +1,45 @@
+algorithms:
+
+  BraTS23_1:
+    meta:
+      authors: Andriy Myronenko, et al.
+      paper: TODO
+      challenge: BraTS23 BraTS-Africa Segmentation
+      rank: 1st
+      year: 2023
+    run_args:
+      docker_image: brainles/brats23_africa_nvauto:latest
+      input_name_schema: "BraTS-SSA-{id:05d}-000"
+      requires_root: true
+      parameters_file: true
+      shm_size: "32gb"
+
+  BraTS23_2:
+    meta:
+      authors: Alyssa R Amod, et al.
+      paper: N/A
+      challenge: BraTS23 BraTS-Africa Segmentation
+      rank: 2nd
+      year: 2023
+    run_args:
+      docker_image: brainles/brats23_africa_sparkunn:latest
+      input_name_schema: "BraTS-SSA-{id:05d}-000"
+      requires_root: false
+      parameters_file: true
+    weights:
+      record_id: "13373752"
+      param_name: "ckpts_path"
+  BraTS23_3:
+    meta:
+      authors: Ziyan Huang, et al.
+      paper: N/A
+      challenge: BraTS23 BraTS-Africa Segmentation
+      rank: 3rd
+      year: 2023
+    run_args:
+      docker_image: brainles/brats23_africa_blackbean:latest
+      input_name_schema: "BraTS-SSA-{id:05d}-000"
+      requires_root: true
+      parameters_file: true
+      cpu_compatible: true
+

brats/algorithms/meningioma.yml

@@ -3,7 +3,9 @@ algorithms:
     meta:
       authors: Andriy Myronenko, et al.
       paper: N/A
-      challenge: BraTS23 Meningioma Segmentation (1st place)
+      challenge: BraTS23 Meningioma Segmentation
+      rank: 1st
+      year: 2023
     run_args:
       docker_image: brainles/brats23_meningioma_nvauto:latest 
       input_name_schema: "BraTS-MEN-{id:05d}-000"
@@ -15,7 +17,9 @@ algorithms:
     meta:
       authors: Ziyan Huang
       paper: N/A
-      challenge: BraTS23 Meningioma Segmentation (2nd place)
+      challenge: BraTS23 Meningioma Segmentation
+      rank: 2nd
+      year: 2023
     run_args:
       docker_image: brainles/brats23_meningioma_blackbean:latest
       input_name_schema: "BraTS-MEN-{id:05d}-000"
@@ -28,7 +32,9 @@ algorithms:
     meta:
       authors: Zhifan Jiang et al.
       paper: N/A
-      challenge: BraTS23 Meningioma Segmentation (3rd place)
+      challenge: BraTS23 Meningioma Segmentation
+      rank: 3rd
+      year: 2023
     run_args:
       docker_image: brainles/brats23_meningioma_cnmc_pmi2023:latest
       input_name_schema: "BraTS-MEN-{id:05d}-000"