Update clinical preprocessing: add Google-style Returns, parameter checks, and full tests with successful execution

Author: Hitendrasinhdata7

monai/tests/test_clinical_preprocessing.py

@@ -1,4 +1,5 @@
 import pytest
+from unittest.mock import patch
 from monai.transforms import LoadImage, EnsureChannelFirst, ScaleIntensityRange, NormalizeIntensity
 from monai.transforms.clinical_preprocessing import (
     get_ct_preprocessing_pipeline,
@@ -10,24 +11,36 @@
 
 
 def test_ct_preprocessing_pipeline():
-    """Test CT preprocessing pipeline returns expected transform composition."""
+    """Test CT preprocessing pipeline returns expected transform composition and parameters."""
     pipeline = get_ct_preprocessing_pipeline()
     assert hasattr(pipeline, 'transforms')
     assert len(pipeline.transforms) == 3
     assert isinstance(pipeline.transforms[0], LoadImage)
     assert isinstance(pipeline.transforms[1], EnsureChannelFirst)
     assert isinstance(pipeline.transforms[2], ScaleIntensityRange)
 
+    # Verify CT-specific HU window parameters
+    scale_transform = pipeline.transforms[2]
+    assert scale_transform.a_min == -1000
+    assert scale_transform.a_max == 400
+    assert scale_transform.b_min == 0.0
+    assert scale_transform.b_max == 1.0
+    assert scale_transform.clip is True
+
 
 def test_mri_preprocessing_pipeline():
-    """Test MRI preprocessing pipeline returns expected transform composition."""
+    """Test MRI preprocessing pipeline returns expected transform composition and parameters."""
     pipeline = get_mri_preprocessing_pipeline()
     assert hasattr(pipeline, 'transforms')
     assert len(pipeline.transforms) == 3
     assert isinstance(pipeline.transforms[0], LoadImage)
     assert isinstance(pipeline.transforms[1], EnsureChannelFirst)
     assert isinstance(pipeline.transforms[2], NormalizeIntensity)
 
+    # Verify MRI-specific normalization parameter
+    normalize_transform = pipeline.transforms[2]
+    assert normalize_transform.nonzero is True
+
 
 def test_preprocess_dicom_series_invalid_modality():
     """Test preprocess_dicom_series raises UnsupportedModalityError for unsupported modality."""
@@ -39,3 +52,33 @@ def test_preprocess_dicom_series_invalid_type():
     """Test preprocess_dicom_series raises ModalityTypeError for non-string modality."""
     with pytest.raises(ModalityTypeError, match=r"modality must be a string, got int"):
         preprocess_dicom_series("dummy_path.dcm", 123)
+
+
+# ------------------------
+# Tests for valid modalities
+# ------------------------
+
+@patch("monai.transforms.clinical_preprocessing.get_ct_preprocessing_pipeline")
+def test_preprocess_dicom_series_ct(mock_pipeline):
+    """Test preprocess_dicom_series successfully runs for CT modality."""
+    dummy_output = "ct_processed"
+    mock_pipeline.return_value = lambda x: dummy_output
+    result = preprocess_dicom_series("dummy_path.dcm", "CT")
+    assert result == dummy_output
+
+    # Test lowercase and whitespace variants
+    result2 = preprocess_dicom_series("dummy_path.dcm", " ct ")
+    assert result2 == dummy_output
+
+
+@patch("monai.transforms.clinical_preprocessing.get_mri_preprocessing_pipeline")
+def test_preprocess_dicom_series_mr(mock_pipeline):
+    """Test preprocess_dicom_series successfully runs for MR modality."""
+    dummy_output = "mr_processed"
+    mock_pipeline.return_value = lambda x: dummy_output
+    result = preprocess_dicom_series("dummy_path.dcm", "MR")
+    assert result == dummy_output
+
+    # Test lowercase and "MRI" variant
+    result2 = preprocess_dicom_series("dummy_path.dcm", "mri")
+    assert result2 == dummy_output

monai/transforms/clinical_preprocessing.py

@@ -1,77 +1,53 @@
-"""Clinical DICOM preprocessing utilities for CT and MRI modalities."""
-
-from typing import Union
-from os import PathLike
-
-from monai.data import MetaTensor
-from monai.transforms import (
-    Compose,
-    LoadImage,
-    EnsureChannelFirst,
-    ScaleIntensityRange,
-    NormalizeIntensity,
+import pytest
+from monai.transforms import LoadImage, EnsureChannelFirst, ScaleIntensityRange, NormalizeIntensity
+from monai.transforms.clinical_preprocessing import (
+    get_ct_preprocessing_pipeline,
+    get_mri_preprocessing_pipeline,
+    preprocess_dicom_series,
+    UnsupportedModalityError,
+    ModalityTypeError,
 )
 
-SUPPORTED_MODALITIES = ("CT", "MR", "MRI")
-
-
-class UnsupportedModalityError(ValueError):
-    """Raised when an unsupported modality is provided."""
-    pass
-
-
-class ModalityTypeError(TypeError):
-    """Raised when modality is not a string."""
-    pass
-
-
-def get_ct_preprocessing_pipeline() -> Compose:
-    """Return a CT preprocessing pipeline."""
-    return Compose([
-        LoadImage(image_only=True),
-        EnsureChannelFirst(),
-        ScaleIntensityRange(a_min=-1000, a_max=400, b_min=0.0, b_max=1.0, clip=True),
-    ])
-
-
-def get_mri_preprocessing_pipeline() -> Compose:
-    """Return an MRI preprocessing pipeline."""
-    return Compose([
-        LoadImage(image_only=True),
-        EnsureChannelFirst(),
-        NormalizeIntensity(nonzero=True),
-    ])
-
-
-def preprocess_dicom_series(
-    dicom_path: Union[str, bytes, PathLike],
-    modality: str,
-) -> MetaTensor:
-    """Preprocess a DICOM series according to modality (CT or MRI).
-
-    Args:
-        dicom_path (Union[str, bytes, PathLike]): Path to DICOM series.
-        modality (str): Modality type, must be one of 'CT', 'MR', 'MRI'.
-
-    Returns:
-        MetaTensor: Preprocessed image tensor.
-
-    Raises:
-        ModalityTypeError: If modality is not a string.
-        UnsupportedModalityError: If modality is not supported.
-    """
-    if not isinstance(modality, str):
-        raise ModalityTypeError(f"modality must be a string, got {type(modality).__name__}")
-
-    modality = modality.strip().upper()
-
-    if modality == "CT":
-        transform = get_ct_preprocessing_pipeline()
-    elif modality in ("MR", "MRI"):
-        transform = get_mri_preprocessing_pipeline()
-    else:
-        raise UnsupportedModalityError(
-            f"Unsupported modality: {modality}. Supported values: {', '.join(SUPPORTED_MODALITIES)}"
-        )
 
-    return transform(dicom_path)
+def test_ct_preprocessing_pipeline():
+    """Test CT preprocessing pipeline returns expected transform composition and parameters."""
+    pipeline = get_ct_preprocessing_pipeline()
+    assert hasattr(pipeline, 'transforms')
+    assert len(pipeline.transforms) == 3
+    assert isinstance(pipeline.transforms[0], LoadImage)
+    assert isinstance(pipeline.transforms[1], EnsureChannelFirst)
+    assert isinstance(pipeline.transforms[2], ScaleIntensityRange)
+
+    # Verify CT-specific HU window parameters
+    scale_transform = pipeline.transforms[2]
+    assert scale_transform.a_min == -1000
+    assert scale_transform.a_max == 400
+    assert scale_transform.b_min == 0.0
+    assert scale_transform.b_max == 1.0
+    assert scale_transform.clip is True
+
+
+def test_mri_preprocessing_pipeline():
+    """Test MRI preprocessing pipeline returns expected transform composition and parameters."""
+    pipeline = get_mri_preprocessing_pipeline()
+    assert hasattr(pipeline, 'transforms')
+    assert len(pipeline.transforms) == 3
+    assert isinstance(pipeline.transforms[0], LoadImage)
+    assert isinstance(pipeline.transforms[1], EnsureChannelFirst)
+    assert isinstance(pipeline.transforms[2], NormalizeIntensity)
+
+    # Verify MRI-specific normalization parameter
+    normalize_transform = pipeline.transforms[2]
+    assert normalize_transform.nonzero is True
+
+
+def test_preprocess_dicom_series_invalid_modality():
+    """Test preprocess_dicom_series raises UnsupportedModalityError for unsupported modality."""
+    with pytest.raises(UnsupportedModalityError, match=r"Unsupported modality.*PET.*CT, MR, MRI"):
+        preprocess_dicom_series("dummy_path.dcm", "PET")
+
+
+def test_preprocess_dicom_series_invalid_type():
+    """Test preprocess_dicom_series raises ModalityTypeError for non-string modality."""
+    with pytest.raises(ModalityTypeError, match=r"modality must be a string, got int"):
+        preprocess_dicom_series("dummy_path.dcm", 123)