Fix CI compliance for clinical preprocessing

- Add proper copyright headers
- Fix type hints and imports
- Follow MONAI coding standards
- Improve test coverage

Signed-off-by: Hitendrasinh Rathod <[email protected]>

Author: Hitendrasinhdata7

monai/tests/test_clinical_preprocessing.py

@@ -22,6 +22,7 @@
     get_ct_preprocessing_pipeline,
     get_mri_preprocessing_pipeline,
     preprocess_dicom_series,
+    preprocess_medical_image,
 )
 
 
@@ -64,6 +65,11 @@ def test_invalid_modality_type():
 
     assert "modality must be a string" in str(exc.value)
 
+    with pytest.raises(ModalityTypeError) as exc:
+        preprocess_medical_image("dummy", None)
+
+    assert "modality must be a string" in str(exc.value)
+
 
 def test_unsupported_modality():
     """Test unsupported modality."""
@@ -76,15 +82,39 @@ def test_unsupported_modality():
     assert "MR" in msg
     assert "MRI" in msg
 
+    with pytest.raises(UnsupportedModalityError) as exc:
+        preprocess_medical_image("dummy", "PET")
+
+    msg = str(exc.value)
+    assert "Unsupported modality" in msg
+    assert "CT" in msg
+    assert "MR" in msg
+    assert "MRI" in msg
+
 
 @patch("monai.transforms.clinical_preprocessing.LoadImage")
 def test_modality_case_insensitivity(mock_load):
-    """Test case-insensitive modality handling."""
+    """Test case-insensitive modality handling with whitespace trimming."""
     mock_load.return_value = Mock(return_value=Mock())
 
-    for modality in ["CT", "ct", "Ct", "CT ", "MR", "mr", "MRI", "mri", " MrI "]:
+    test_cases = [
+        ("CT", True),
+        ("ct", True),
+        ("Ct", True),
+        ("CT ", True),
+        (" CT", True),
+        ("MR", True),
+        ("mr", True),
+        ("MRI", True),
+        ("mri", True),
+        (" MrI ", True),
+    ]
+
+    for modality, _ in test_cases:
         result = preprocess_dicom_series("dummy.dcm", modality)
-        assert result is not None
+        assert result is not None, f"Failed for modality: '{modality}'"
+        result2 = preprocess_medical_image("dummy.dcm", modality)
+        assert result2 is not None, f"preprocess_medical_image failed for modality: '{modality}'"
 
 
 @patch("monai.transforms.clinical_preprocessing.LoadImage")
@@ -93,6 +123,24 @@ def test_mr_modality_distinct(mock_load):
     mock_load.return_value = Mock(return_value=Mock())
     result = preprocess_dicom_series("dummy.dcm", "MR")
     assert result is not None
+    result2 = preprocess_medical_image("dummy.dcm", "MR")
+    assert result2 is not None
+
+
+@patch("monai.transforms.clinical_preprocessing.LoadImage")
+def test_edge_cases(mock_load):
+    """Test edge cases for modality input."""
+    mock_load.return_value = Mock(return_value=Mock())
+
+    with pytest.raises(UnsupportedModalityError):
+        preprocess_dicom_series("dummy.dcm", "")
+
+    with pytest.raises(UnsupportedModalityError):
+        preprocess_dicom_series("dummy.dcm", "   ")
+
+    long_modality = "CT" * 100
+    with pytest.raises(UnsupportedModalityError):
+        preprocess_dicom_series("dummy.dcm", long_modality)
 
 
 def test_preprocess_dicom_series_integration(tmp_path):
@@ -106,3 +154,6 @@ def test_preprocess_dicom_series_integration(tmp_path):
         result = preprocess_dicom_series(str(test_file), modality)
         assert result is not None
         assert hasattr(result, "shape")
+        result2 = preprocess_medical_image(str(test_file), modality)
+        assert result2 is not None
+        assert hasattr(result2, "shape")

monai/transforms/clinical_preprocessing.py

@@ -15,7 +15,10 @@
 This module provides modality-specific preprocessing pipelines for common medical imaging modalities.
 """
 
-from typing import Any
+from typing import Union
+
+import numpy as np
+import torch
 
 from monai.transforms import (
     Compose,
@@ -42,6 +45,10 @@ def get_ct_preprocessing_pipeline() -> Compose:
         Compose: Transform composition for CT preprocessing.
             Applies Hounsfield Unit (HU) windowing [-1000, 400] scaled to [0, 1].
             This range captures lung (-1000 to -400 HU) and soft tissue (0 to 100 HU) contrast.
+
+    Note:
+        Output will be a single-channel tensor with shape (1, H, W, D)
+        and values in range [0, 1].
     """
     return Compose(
         [
@@ -66,6 +73,10 @@ def get_mri_preprocessing_pipeline() -> Compose:
         Compose: Transform composition for MRI preprocessing.
             Normalizes intensities using nonzero voxels only, excluding background regions
             typical in MRI acquisitions.
+
+    Note:
+        Output will be a single-channel tensor with shape (1, H, W, D)
+        normalized based on nonzero voxel statistics.
     """
     return Compose(
         [
@@ -76,23 +87,24 @@ def get_mri_preprocessing_pipeline() -> Compose:
     )
 
 
-def preprocess_dicom_series(path: str, modality: str) -> Any:
-    """Preprocess a DICOM series or file based on imaging modality.
+def preprocess_medical_image(path: str, modality: str) -> Union[torch.Tensor, np.ndarray]:
+    """
+    Preprocess a medical image based on imaging modality.
 
     Args:
-        path: Path to the DICOM file or directory containing a DICOM series.
+        path: Path to the medical image file. Supports various formats including
+            DICOM, NIfTI, and others supported by MONAI's LoadImage transform.
         modality: Imaging modality. Supported values are "CT", "MR", and "MRI" (case-insensitive).
 
     Returns:
-        Any: Preprocessed image data.
+        Preprocessed image data as a tensor or numpy array.
 
     Raises:
         ModalityTypeError: If modality is not a string.
         UnsupportedModalityError: If the provided modality is not supported.
     """
     if not isinstance(modality, str):
-        error_msg = "modality must be a string"
-        raise ModalityTypeError(error_msg)
+        raise ModalityTypeError("modality must be a string")
 
     modality_clean = modality.strip().upper()
 
@@ -101,19 +113,40 @@ def preprocess_dicom_series(path: str, modality: str) -> Any:
     elif modality_clean == "CT":
         pipeline = get_ct_preprocessing_pipeline()
     else:
-        error_msg = (
-            f"Unsupported modality '{modality}'. "
-            f"Supported modalities: CT, MR, MRI"
+        raise UnsupportedModalityError(
+            f"Unsupported modality '{modality}'. Supported modalities: CT, MR, MRI"
         )
-        raise UnsupportedModalityError(error_msg)
 
     return pipeline(path)
 
 
+# Keep the old function name for backward compatibility
+def preprocess_dicom_series(path: str, modality: str) -> Union[torch.Tensor, np.ndarray]:
+    """
+    Preprocess a DICOM series or file based on imaging modality.
+
+    Note: This function also supports other medical image formats
+    (NIfTI, etc.) through MONAI's LoadImage transform.
+
+    Args:
+        path: Path to the DICOM file or directory containing a DICOM series.
+        modality: Imaging modality. Supported values are "CT", "MR", and "MRI" (case-insensitive).
+
+    Returns:
+        Preprocessed image data.
+
+    Raises:
+        ModalityTypeError: If modality is not a string.
+        UnsupportedModalityError: If the provided modality is not supported.
+    """
+    return preprocess_medical_image(path, modality)
+
+
 __all__ = [
     "ModalityTypeError",
     "UnsupportedModalityError",
     "get_ct_preprocessing_pipeline",
     "get_mri_preprocessing_pipeline",
     "preprocess_dicom_series",
-]
+    "preprocess_medical_image",
+]