Merge pull request #54 from BrainLesion/53-split-post-op-glioma-algor…

…ithms-into-own-class

53 split post op glioma algorithms into own class

README.md

@@ -40,17 +40,17 @@ pip install brats
 ## Available Algorithms and Usage
 
 ### Segmentation
-<details open>
+<details>
 
-<summary> <strong> Adult Glioma Segmentation </strong> </summary>
+<summary> <strong> Adult Glioma Segmentation (Pre Treatment) </strong> </summary>
 <br>
 
 
 ```python
-from brats import AdultGliomaSegmenter
-from brats.constants import AdultGliomaAlgorithms
+from brats import AdultGliomaPreTreatmentSegmenter
+from brats.constants import AdultGliomaPreTreatmentAlgorithms
 
-segmenter = AdultGliomaSegmenter(algorithm=AdultGliomaAlgorithms.BraTS23_1, cuda_devices="0")
+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",
@@ -61,16 +61,43 @@ segmenter.infer_single(
 )
 ```
 
-**Class:** `brats.AdultGliomaSegmenter` ([Docs](https://brats.readthedocs.io/en/latest/core/segmentation_algorithms.html#brats.core.segmentation_algorithms.AdultGliomaSegmenter))
+**Class:** `brats.AdultGliomaPreTreatmentSegmenter` ([Docs](https://brats.readthedocs.io/en/latest/core/segmentation_algorithms.html#brats.core.segmentation_algorithms.AdultGliomaPreTreatmentSegmenter))
+
+| Year | Rank | Author                            | Paper                                      | CPU Support | Key Enum                                                                                                                             |
+| ---- | ---- | --------------------------------- | ------------------------------------------ | ----------- | ------------------------------------------------------------------------------------------------------------------------------------ |
+| 2023 | 1st  | _André Ferreira, et al._          | [Link](https://arxiv.org/abs/2402.17317v1) | &#x274C;    | [BraTS23_1](https://brats.readthedocs.io/en/latest/utils/utils.html#brats.constants.**AdultGliomaPreTreatmentAlgorithms**.BraTS23_1) |
+| 2023 | 2nd  | _Andriy Myronenko, et al._        | N/A                                        | &#x274C;    | [BraTS23_2](https://brats.readthedocs.io/en/latest/utils/utils.html#brats.constants.**AdultGliomaPreTreatmentAlgorithms**.BraTS23_2) |
+| 2023 | 3rd  | _Fadillah Adamsyah Maani, et al._ | N/A                                        | &#x274C;    | [BraTS23_3](https://brats.readthedocs.io/en/latest/utils/utils.html#brats.constants.**AdultGliomaPreTreatmentAlgorithms**.BraTS23_3) |
+
+</details>
+
+<details>
+<summary> <strong> Adult Glioma Segmentation Post Treatment </strong> </summary>
+<br>
+
+
+```python
+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](https://brats.readthedocs.io/en/latest/core/segmentation_algorithms.html#brats.core.segmentation_algorithms.AdultGliomaPostTreatmentSegmenter))
 
-| Year | Rank | Author                            | Paper                                      | CPU Support | Key Enum                                                                                                             |
-| ---- | ---- | --------------------------------- | ------------------------------------------ | ----------- | -------------------------------------------------------------------------------------------------------------------- |
-| 2024 | 1st  | _André Ferreira, et al._          | N/A                                        | &#x274C;    | [BraTS24_1](https://brats.readthedocs.io/en/latest/utils/utils.html#brats.constants.AdultGliomaAlgorithms.BraTS24_1) |
-| 2024 | 2nd  | _Team kimbab_                     | N/A                                        | &#x274C;    | [BraTS24_2](https://brats.readthedocs.io/en/latest/utils/utils.html#brats.constants.AdultGliomaAlgorithms.BraTS24_2) |
-| 2024 | 3rd  | _Adrian Celaya_                   | N/A                                        | &#x2705;    | [BraTS24_3](https://brats.readthedocs.io/en/latest/utils/utils.html#brats.constants.AdultGliomaAlgorithms.BraTS24_3) |
-| 2023 | 1st  | _André Ferreira, et al._          | [Link](https://arxiv.org/abs/2402.17317v1) | &#x274C;    | [BraTS23_1](https://brats.readthedocs.io/en/latest/utils/utils.html#brats.constants.AdultGliomaAlgorithms.BraTS23_1) |
-| 2023 | 2nd  | _Andriy Myronenko, et al._        | N/A                                        | &#x274C;    | [BraTS23_2](https://brats.readthedocs.io/en/latest/utils/utils.html#brats.constants.AdultGliomaAlgorithms.BraTS23_2) |
-| 2023 | 3rd  | _Fadillah Adamsyah Maani, et al._ | N/A                                        | &#x274C;    | [BraTS23_3](https://brats.readthedocs.io/en/latest/utils/utils.html#brats.constants.AdultGliomaAlgorithms.BraTS23_3) |
+| Year | Rank | Author                   | Paper | CPU Support | Key Enum                                                                                                                          |
+| ---- | ---- | ------------------------ | ----- | ----------- | --------------------------------------------------------------------------------------------------------------------------------- |
+| 2024 | 1st  | _André Ferreira, et al._ | N/A   | &#x274C;    | [BraTS24_1](https://brats.readthedocs.io/en/latest/utils/utils.html#brats.constants.AdultGliomaPostTreatmentAlgorithms.BraTS24_1) |
+| 2024 | 2nd  | _Team kimbab_            | N/A   | &#x274C;    | [BraTS24_2](https://brats.readthedocs.io/en/latest/utils/utils.html#brats.constants.AdultGliomaPostTreatmentAlgorithms.BraTS24_2) |
+| 2024 | 3rd  | _Adrian Celaya_          | N/A   | &#x2705;    | [BraTS24_3](https://brats.readthedocs.io/en/latest/utils/utils.html#brats.constants.AdultGliomaPostTreatmentAlgorithms.BraTS24_3) |
 
 </details>
 

brats/__init__.py

@@ -1,6 +1,7 @@
 from brats.core.inpainting_algorithms import Inpainter
 from brats.core.segmentation_algorithms import (
-    AdultGliomaSegmenter,
+    AdultGliomaPostTreatmentSegmenter,
+    AdultGliomaPreTreatmentSegmenter,
     AfricaSegmenter,
     MeningiomaSegmenter,
     MetastasesSegmenter,

brats/constants.py

@@ -26,8 +26,8 @@ class Algorithms(str, Enum):
     pass
 
 
-class AdultGliomaAlgorithms(Algorithms):
-    """Constants for the available adult glioma segmentation algorithms."""
+class AdultGliomaPostTreatmentAlgorithms(Algorithms):
+    """Constants for the available adult glioma post treatment segmentation algorithms."""
 
     BraTS24_1 = "BraTS24_1"
     """ BraTS24 Adult Glioma Segmentation 1st place """
@@ -36,6 +36,10 @@ class AdultGliomaAlgorithms(Algorithms):
     BraTS24_3 = "BraTS24_3"
     """ BraTS24 Adult Glioma Segmentation 3rd place """
 
+
+class AdultGliomaPreTreatmentAlgorithms(Algorithms):
+    """Constants for the available adult glioma pre treatment segmentation algorithms."""
+
     BraTS23_1 = "BraTS23_1"
     """BraTS23 Adult Glioma Segmentation 1st place (GPU only)"""
     BraTS23_2 = "BraTS23_2"
@@ -145,7 +149,12 @@ class MissingMRIAlgorithms(Algorithms):
 ADDITIONAL_FILES_FOLDER = DATA_DIR / "additional_files"
 
 # META DATA FILE PATHS
-ADULT_GLIOMA_SEGMENTATION_ALGORITHMS = META_DIR / "adult_glioma.yml"
+ADULT_GLIOMA_PRE_TREATMENT_SEGMENTATION_ALGORITHMS = (
+    META_DIR / "adult_glioma_pre_treatment.yml"
+)
+ADULT_GLIOMA_POST_TREATMENT_SEGMENTATION_ALGORITHMS = (
+    META_DIR / "adult_glioma_post_treatment.yml"
+)
 MENINGIOMA_SEGMENTATION_ALGORITHMS = META_DIR / "meningioma.yml"
 PEDIATRIC_SEGMENTATION_ALGORITHMS = META_DIR / "pediatric.yml"
 AFRICA_SEGMENTATION_ALGORITHMS = META_DIR / "africa.yml"

brats/core/segmentation_algorithms.py

@@ -9,12 +9,14 @@
 
 from brats.core.brats_algorithm import BraTSAlgorithm
 from brats.constants import (
-    ADULT_GLIOMA_SEGMENTATION_ALGORITHMS,
+    ADULT_GLIOMA_POST_TREATMENT_SEGMENTATION_ALGORITHMS,
+    ADULT_GLIOMA_PRE_TREATMENT_SEGMENTATION_ALGORITHMS,
     AFRICA_SEGMENTATION_ALGORITHMS,
     MENINGIOMA_SEGMENTATION_ALGORITHMS,
     METASTASES_SEGMENTATION_ALGORITHMS,
     PEDIATRIC_SEGMENTATION_ALGORITHMS,
-    AdultGliomaAlgorithms,
+    AdultGliomaPostTreatmentAlgorithms,
+    AdultGliomaPreTreatmentAlgorithms,
     AfricaAlgorithms,
     Algorithms,
     MeningiomaAlgorithms,
@@ -184,24 +186,47 @@ def infer_batch(
         )
 
 
-class AdultGliomaSegmenter(SegmentationAlgorithm):
-    """Provides algorithms to perform tumor segmentation on adult glioma MRI data.
+class AdultGliomaPreTreatmentSegmenter(SegmentationAlgorithm):
+    """Provides algorithms to perform tumor segmentation on adult glioma pre treatment MRI data.
 
     Args:
-        algorithm (AdultGliomaAlgorithms, optional): Select an algorithm. Defaults to AdultGliomaAlgorithms.BraTS23_1.
+        algorithm (AdultGliomaPreTreatmentAlgorithms, optional): Select an algorithm. Defaults to AdultGliomaPreTreatmentAlgorithms.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: AdultGliomaAlgorithms = AdultGliomaAlgorithms.BraTS23_1,
+        algorithm: AdultGliomaPreTreatmentAlgorithms = AdultGliomaPreTreatmentAlgorithms.BraTS23_1,
         cuda_devices: Optional[str] = "0",
         force_cpu: bool = False,
     ):
         super().__init__(
             algorithm=algorithm,
-            algorithms_file_path=ADULT_GLIOMA_SEGMENTATION_ALGORITHMS,
+            algorithms_file_path=ADULT_GLIOMA_PRE_TREATMENT_SEGMENTATION_ALGORITHMS,
+            cuda_devices=cuda_devices,
+            force_cpu=force_cpu,
+        )
+
+
+class AdultGliomaPostTreatmentSegmenter(SegmentationAlgorithm):
+    """Provides algorithms to perform tumor segmentation on adult glioma post treatment MRI data.
+
+    Args:
+        algorithm (AdultGliomaPostTreatmentAlgorithms, optional): Select an algorithm. Defaults to AdultGliomaPostTreatmentAlgorithms.BraTS24_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: AdultGliomaPostTreatmentAlgorithms = AdultGliomaPostTreatmentAlgorithms.BraTS24_1,
+        cuda_devices: Optional[str] = "0",
+        force_cpu: bool = False,
+    ):
+        super().__init__(
+            algorithm=algorithm,
+            algorithms_file_path=ADULT_GLIOMA_POST_TREATMENT_SEGMENTATION_ALGORITHMS,
             cuda_devices=cuda_devices,
             force_cpu=force_cpu,
         )

brats/data/meta/adult_glioma.yml → brats/data/meta/adult_glioma_post_treatment.yml

@@ -1,9 +1,8 @@
 constants:
   input_name_schema: &input_name_schema "BraTS-GLI-{id:05d}-000"
-  challenge: &challenge "Adult Glioma Segmentation"
+  challenge: &challenge "Adult Glioma Segmentation (Post Treatment)"
   years:
     2024: &year_2024 2024
-    2023: &year_2023 2023
   ranks:
     1st: &rank_1 1st
     2nd: &rank_2 2nd
@@ -61,51 +60,4 @@ algorithms:
     additional_files:
       record_id: "14411467"
       param_name: ["mist_models", "mist_config", "mist_dataset"]
-      param_path: ["models", "config.json", "dataset.json"]
-
-##### 2023 #####
-
-  BraTS23_1:
-    meta:
-      authors: André Ferreira, et al.
-      paper: https://arxiv.org/abs/2402.17317v1
-      challenge: *challenge
-      rank: *rank_1
-      year: *year_2023
-    run_args:
-      docker_image: brainles/brats23_faking_it:latest
-      input_name_schema: *input_name_schema
-      requires_root: true
-      parameters_file: false
-      shm_size: "2gb"
-
-  BraTS23_2:
-    meta:
-      authors: Andriy Myronenko, et al.
-      paper: N/A
-      challenge: *challenge
-      rank: *rank_2
-      year: *year_2023
-    run_args:
-      docker_image: brainles/brats23_nvauto:latest
-      input_name_schema: *input_name_schema
-      requires_root: true
-      parameters_file: true
-      shm_size: "32gb"
-
-  BraTS23_3:
-    meta:
-      authors: Fadillah Adamsyah Maani, et al.
-      paper: N/A
-      challenge: *challenge
-      rank: *rank_3
-      year: *year_2023
-    run_args:
-      docker_image: brainles/brats23_biomedmbz:latest
-      input_name_schema: *input_name_schema
-      requires_root: false
-      parameters_file: true
-      shm_size: "2gb"
-    additional_files:
-      record_id: "11573315"
-      param_name: ["checkpoint_dir"]
+      param_path: ["models", "config.json", "dataset.json"]

brats/data/meta/adult_glioma_pre_treatment.yml

@@ -0,0 +1,59 @@
+constants:
+  input_name_schema: &input_name_schema "BraTS-GLI-{id:05d}-000"
+  challenge: &challenge "Adult Glioma Segmentation (Pre Treatment)"
+  years:
+    2023: &year_2023 2023
+  ranks:
+    1st: &rank_1 1st
+    2nd: &rank_2 2nd
+    3rd: &rank_3 3rd
+
+
+algorithms:
+
+##### 2023 #####
+
+  BraTS23_1:
+    meta:
+      authors: André Ferreira, et al.
+      paper: https://arxiv.org/abs/2402.17317v1
+      challenge: *challenge
+      rank: *rank_1
+      year: *year_2023
+    run_args:
+      docker_image: brainles/brats23_faking_it:latest
+      input_name_schema: *input_name_schema
+      requires_root: true
+      parameters_file: false
+      shm_size: "2gb"
+
+  BraTS23_2:
+    meta:
+      authors: Andriy Myronenko, et al.
+      paper: N/A
+      challenge: *challenge
+      rank: *rank_2
+      year: *year_2023
+    run_args:
+      docker_image: brainles/brats23_nvauto:latest
+      input_name_schema: *input_name_schema
+      requires_root: true
+      parameters_file: true
+      shm_size: "32gb"
+
+  BraTS23_3:
+    meta:
+      authors: Fadillah Adamsyah Maani, et al.
+      paper: N/A
+      challenge: *challenge
+      rank: *rank_3
+      year: *year_2023
+    run_args:
+      docker_image: brainles/brats23_biomedmbz:latest
+      input_name_schema: *input_name_schema
+      requires_root: false
+      parameters_file: true
+      shm_size: "2gb"
+    additional_files:
+      record_id: "11573315"
+      param_name: ["checkpoint_dir"]

docs/source/core/segmentation_algorithms.rst

@@ -1,6 +1,6 @@
 Segmentation Algorithms
 ========================
 
-The following classes provide segmentation algorithms from several BraTS challenges.
+The following classes provide algorithms from several BraTS segmentation challenges.
 
 .. automodule:: brats.core.segmentation_algorithms

tests/core/test_brats_algorithm.py

@@ -4,7 +4,7 @@
 import tempfile
 import shutil
 
-from brats import AdultGliomaSegmenter
+from brats import AdultGliomaPostTreatmentSegmenter
 from brats.constants import OUTPUT_NAME_SCHEMA
 
 
@@ -31,7 +31,7 @@ def setUp(self):
             file.touch()
 
         # the core inference method is the same for all segmentation and inpainting algorithms, we use AdultGliomaSegmenter as an example during testing
-        self.segmenter = AdultGliomaSegmenter()
+        self.segmenter = AdultGliomaPostTreatmentSegmenter()
 
     def tearDown(self):
         # Remove the temporary directory after the test