junifer 0.0.6.dev311__tar.gz → 0.0.6.dev317__tar.gz

{junifer-0.0.6.dev311 → junifer-0.0.6.dev317}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: junifer
-Version: 0.0.6.dev311
+Version: 0.0.6.dev317
 Summary: JUelich NeuroImaging FEature extractoR
 Author-email: Fede Raimondo <f.raimondo@fz-juelich.de>, Synchon Mandal <s.mandal@fz-juelich.de>
 Maintainer-email: Fede Raimondo <f.raimondo@fz-juelich.de>, Synchon Mandal <s.mandal@fz-juelich.de>

junifer-0.0.6.dev317/docs/changes/newsfragments/408.enh

@@ -0,0 +1 @@
+Update Preprocessors to sync data their paths so that the results are idempotent by `Synchon Mandal`_

junifer-0.0.6.dev317/docs/changes/newsfragments/408.feature

@@ -0,0 +1 @@
+Allow masks to be warped, if found, in :class:`.SpaceWarper` by `Synchon Mandal`_

{junifer-0.0.6.dev311 → junifer-0.0.6.dev317}/junifer/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.0.6.dev311'
-__version_tuple__ = version_tuple = (0, 0, 6, 'dev311')
+__version__ = version = '0.0.6.dev317'
+__version_tuple__ = version_tuple = (0, 0, 6, 'dev317')

{junifer-0.0.6.dev311 → junifer-0.0.6.dev317}/junifer/preprocess/confounds/fmriprep_confound_remover.py

@@ -12,6 +12,7 @@ from typing import (
     Union,
 )
 
+import nibabel as nib
 import numpy as np
 import pandas as pd
 from nilearn import image as nimg
@@ -19,6 +20,7 @@ from nilearn._utils.niimg_conversions import check_niimg_4d
 
 from ...api.decorators import register_preprocessor
 from ...data import get_data
+from ...pipeline import WorkDirManager
 from ...typing import Dependencies
 from ...utils import logger, raise_error
 from ..base import BasePreprocessor
@@ -539,9 +541,17 @@ class fMRIPrepConfoundRemover(BasePreprocessor):
             logger.info(
                 f"Read t_r from NIfTI header: {t_r}",
             )
+
+        # Create element-specific tempdir for storing generated data
+        # and / or mask
+        element_tempdir = WorkDirManager().get_element_tempdir(
+            prefix="fmriprep_confound_remover"
+        )
+
         # Set mask data
         mask_img = None
         if self.masks is not None:
+            # Generate mask
             logger.debug(f"Masking with {self.masks}")
             mask_img = get_data(
                 kind="mask",
@@ -549,13 +559,21 @@ class fMRIPrepConfoundRemover(BasePreprocessor):
                 target_data=input,
                 extra_input=extra_input,
             )
-            # Return the BOLD mask and link it to the BOLD data type dict;
+            # Save generated mask for use later
+            generated_mask_img_path = element_tempdir / "generated_mask.nii.gz"
+            nib.save(mask_img, generated_mask_img_path)
+
+            # Save BOLD mask and link it to the BOLD data type dict;
             # this allows to use "inherit" down the pipeline
             logger.debug("Setting `BOLD.mask`")
             input.update(
                 {
                     "mask": {
+                        # Update path to sync with "data"
+                        "path": generated_mask_img_path,
+                        # Update data
                         "data": mask_img,
+                        # Should be in the same space as target data
                         "space": input["space"],
                     }
                 }
@@ -566,7 +584,9 @@ class fMRIPrepConfoundRemover(BasePreprocessor):
         logger.debug(f"\tstandardize: {self.standardize}")
         logger.debug(f"\tlow_pass: {self.low_pass}")
         logger.debug(f"\thigh_pass: {self.high_pass}")
-        input["data"] = nimg.clean_img(
+
+        # Deconfound data
+        cleaned_img = nimg.clean_img(
             imgs=bold_img,
             detrend=self.detrend,
             standardize=self.standardize,
@@ -576,5 +596,18 @@ class fMRIPrepConfoundRemover(BasePreprocessor):
             t_r=t_r,
             mask_img=mask_img,
         )
+        # Save deconfounded data
+        deconfounded_img_path = element_tempdir / "deconfounded_data.nii.gz"
+        nib.save(cleaned_img, deconfounded_img_path)
+
+        logger.debug("Updating `BOLD`")
+        input.update(
+            {
+                # Update path to sync with "data"
+                "path": deconfounded_img_path,
+                # Update data
+                "data": cleaned_img,
+            }
+        )
 
         return input, None

{junifer-0.0.6.dev311 → junifer-0.0.6.dev317}/junifer/preprocess/smoothing/_afni_smoothing.py

@@ -4,7 +4,7 @@
 # License: AGPL
 
 from typing import (
-    TYPE_CHECKING,
+    Any,
     ClassVar,
     Union,
 )
@@ -16,10 +16,6 @@ from ...typing import Dependencies, ExternalDependencies
 from ...utils import logger, run_ext_cmd
 
 
-if TYPE_CHECKING:
-    from nibabel.nifti1 import Nifti1Image
-
-
 __all__ = ["AFNISmoothing"]
 
 
@@ -41,23 +37,23 @@ class AFNISmoothing:
 
     def preprocess(
         self,
-        data: "Nifti1Image",
+        input: dict[str, Any],
         fwhm: Union[int, float],
-    ) -> "Nifti1Image":
+    ) -> dict[str, Any]:
         """Preprocess using AFNI.
 
         Parameters
         ----------
-        data : Niimg-like object
-            Image(s) to preprocess.
+        input : dict
+            A single input from the Junifer Data object in which to preprocess.
         fwhm : int or float
             Smooth until the value. AFNI estimates the smoothing and then
             applies smoothing to reach ``fwhm``.
 
         Returns
         -------
-        Niimg-like object
-            The preprocessed image(s).
+        dict
+            The ``input`` dictionary with updated values.
 
         Notes
         -----
@@ -71,18 +67,18 @@ class AFNISmoothing:
         """
         logger.info("Smoothing using AFNI")
 
-        # Create component-scoped tempdir
-        tempdir = WorkDirManager().get_tempdir(prefix="afni_smoothing")
-
-        # Save target data to a component-scoped tempfile
-        nifti_in_file_path = tempdir / "input.nii"  # needs to be .nii
-        nib.save(data, nifti_in_file_path)
+        # Create element-scoped tempdir so that the output is
+        # available later as nibabel stores file path reference for
+        # loading on computation
+        element_tempdir = WorkDirManager().get_element_tempdir(
+            prefix="afni_smoothing"
+        )
 
         # Set 3dBlurToFWHM command
-        blur_out_path_prefix = tempdir / "blur"
+        blur_out_path_prefix = element_tempdir / "blur"
         blur_cmd = [
             "3dBlurToFWHM",
-            f"-input {nifti_in_file_path.resolve()}",
+            f"-input {input['path'].resolve()}",
             f"-prefix {blur_out_path_prefix.resolve()}",
             "-automask",
             f"-FWHM {fwhm}",
@@ -90,28 +86,34 @@ class AFNISmoothing:
         # Call 3dBlurToFWHM
         run_ext_cmd(name="3dBlurToFWHM", cmd=blur_cmd)
 
-        # Create element-scoped tempdir so that the blurred output is
-        # available later as nibabel stores file path reference for
-        # loading on computation
-        element_tempdir = WorkDirManager().get_element_tempdir(
-            prefix="afni_blur"
-        )
+        # Read header to get output suffix
+        header = input["data"].header
+        sform_code = header.get_sform(coded=True)[1]
+        if sform_code == 4:
+            output_suffix = "tlrc"
+        else:
+            output_suffix = "orig"
+
         # Convert afni to nifti
-        blur_afni_to_nifti_out_path = (
-            element_tempdir / "output.nii"  # needs to be .nii
+        blur_nifti_out_path = (
+            element_tempdir / "smoothed_data.nii"  # needs to be .nii
         )
         convert_cmd = [
             "3dAFNItoNIFTI",
-            f"-prefix {blur_afni_to_nifti_out_path.resolve()}",
-            f"{blur_out_path_prefix}+orig.BRIK",
+            f"-prefix {blur_nifti_out_path.resolve()}",
+            f"{blur_out_path_prefix}+{output_suffix}.BRIK",
         ]
         # Call 3dAFNItoNIFTI
         run_ext_cmd(name="3dAFNItoNIFTI", cmd=convert_cmd)
 
-        # Load nifti
-        output_data = nib.load(blur_afni_to_nifti_out_path)
-
-        # Delete tempdir
-        WorkDirManager().delete_tempdir(tempdir)
+        logger.debug("Updating smoothed data")
+        input.update(
+            {
+                # Update path to sync with "data"
+                "path": blur_nifti_out_path,
+                # Load nifti
+                "data": nib.load(blur_nifti_out_path),
+            }
+        )
 
-        return output_data  # type: ignore
+        return input

{junifer-0.0.6.dev311 → junifer-0.0.6.dev317}/junifer/preprocess/smoothing/_fsl_smoothing.py

@@ -4,7 +4,7 @@
 # License: AGPL
 
 from typing import (
-    TYPE_CHECKING,
+    Any,
     ClassVar,
 )
 
@@ -15,10 +15,6 @@ from ...typing import Dependencies, ExternalDependencies
 from ...utils import logger, run_ext_cmd
 
 
-if TYPE_CHECKING:
-    from nibabel.nifti1 import Nifti1Image
-
-
 __all__ = ["FSLSmoothing"]
 
 
@@ -40,16 +36,16 @@ class FSLSmoothing:
 
     def preprocess(
         self,
-        data: "Nifti1Image",
+        input: dict[str, Any],
         brightness_threshold: float,
         fwhm: float,
-    ) -> "Nifti1Image":
+    ) -> dict[str, Any]:
         """Preprocess using FSL.
 
         Parameters
         ----------
-        data : Niimg-like object
-            Image(s) to preprocess.
+        input : dict
+            A single input from the Junifer Data object in which to preprocess.
         brightness_threshold : float
             Threshold to discriminate between noise and the underlying image.
             The value should be set greater than the noise level and less than
@@ -59,8 +55,8 @@ class FSLSmoothing:
 
         Returns
         -------
-        Niimg-like object
-            The preprocessed image(s).
+        dict
+            The ``input`` dictionary with updated values.
 
         Notes
         -----
@@ -76,24 +72,17 @@ class FSLSmoothing:
         """
         logger.info("Smoothing using FSL")
 
-        # Create component-scoped tempdir
-        tempdir = WorkDirManager().get_tempdir(prefix="fsl_smoothing")
-
-        # Save target data to a component-scoped tempfile
-        nifti_in_file_path = tempdir / "input.nii.gz"
-        nib.save(data, nifti_in_file_path)
-
         # Create element-scoped tempdir so that the output is
         # available later as nibabel stores file path reference for
         # loading on computation
         element_tempdir = WorkDirManager().get_element_tempdir(
             prefix="fsl_susan"
         )
-        susan_out_path = element_tempdir / "output.nii.gz"
+        susan_out_path = element_tempdir / "smoothed_data.nii.gz"
         # Set susan command
         susan_cmd = [
             "susan",
-            f"{nifti_in_file_path.resolve()}",
+            f"{input['path'].resolve()}",
             f"{brightness_threshold}",
             f"{fwhm}",
             "3",  # dimension
@@ -104,10 +93,14 @@ class FSLSmoothing:
         # Call susan
         run_ext_cmd(name="susan", cmd=susan_cmd)
 
-        # Load nifti
-        output_data = nib.load(susan_out_path)
-
-        # Delete tempdir
-        WorkDirManager().delete_tempdir(tempdir)
+        logger.debug("Updating smoothed data")
+        input.update(
+            {
+                # Update path to sync with "data"
+                "path": susan_out_path,
+                # Load nifti
+                "data": nib.load(susan_out_path),
+            }
+        )
 
-        return output_data  # type: ignore
+        return input

{junifer-0.0.6.dev311 → junifer-0.0.6.dev317}/junifer/preprocess/smoothing/_nilearn_smoothing.py

@@ -4,23 +4,21 @@
 # License: AGPL
 
 from typing import (
-    TYPE_CHECKING,
+    Any,
     ClassVar,
     Literal,
     Union,
 )
 
+import nibabel as nib
 from nilearn import image as nimg
 from numpy.typing import ArrayLike
 
+from ...pipeline import WorkDirManager
 from ...typing import Dependencies
 from ...utils import logger
 
 
-if TYPE_CHECKING:
-    from nibabel.nifti1 import Nifti1Image
-
-
 __all__ = ["NilearnSmoothing"]
 
 
@@ -35,15 +33,15 @@ class NilearnSmoothing:
 
     def preprocess(
         self,
-        data: "Nifti1Image",
+        input: dict[str, Any],
         fwhm: Union[int, float, ArrayLike, Literal["fast"], None],
-    ) -> "Nifti1Image":
+    ) -> dict[str, Any]:
         """Preprocess using nilearn.
 
         Parameters
         ----------
-        data : Niimg-like object
-            Image(s) to preprocess.
+        input : dict
+            A single input from the Junifer Data object in which to preprocess.
         fwhm : scalar, ``numpy.ndarray``, tuple or list of scalar, "fast" or \
                None
             Smoothing strength, as a full-width at half maximum, in
@@ -61,9 +59,32 @@ class NilearnSmoothing:
 
         Returns
         -------
-        Niimg-like object
-            The preprocessed image(s).
+        dict
+            The ``input`` dictionary with updated values.
 
         """
         logger.info("Smoothing using nilearn")
-        return nimg.smooth_img(imgs=data, fwhm=fwhm)  # type: ignore
+
+        # Create element-scoped tempdir so that the output is
+        # available later as nibabel stores file path reference for
+        # loading on computation
+        element_tempdir = WorkDirManager().get_element_tempdir(
+            prefix="nilearn_smoothing"
+        )
+
+        smoothed_img = nimg.smooth_img(imgs=input["data"], fwhm=fwhm)
+
+        # Save smoothed output
+        smoothed_img_path = element_tempdir / "smoothed_data.nii.gz"
+        nib.save(smoothed_img, smoothed_img_path)
+
+        logger.debug("Updating smoothed data")
+        input.update(
+            {
+                # Update path to sync with "data"
+                "path": smoothed_img_path,
+                "data": smoothed_img,
+            }
+        )
+
+        return input

{junifer-0.0.6.dev311 → junifer-0.0.6.dev317}/junifer/preprocess/smoothing/smoothing.py

@@ -164,12 +164,9 @@ class Smoothing(BasePreprocessor):
         elif self.using == "fsl":
             preprocessor = FSLSmoothing()
         # Smooth
-        output = preprocessor.preprocess(  # type: ignore
-            data=input["data"],
+        input = preprocessor.preprocess(
+            input=input,
             **self.smoothing_params,
         )
 
-        # Modify target data
-        input["data"] = output
-
         return input, None

{junifer-0.0.6.dev311 → junifer-0.0.6.dev317}/junifer/preprocess/warping/_ants_warper.py

@@ -58,9 +58,7 @@ class ANTsWarper:
         Returns
         -------
         dict
-            The ``input`` dictionary with modified ``data`` and ``space`` key
-            values and new ``reference`` key whose value points to the
-            reference file used for warping.
+            The ``input`` dictionary with updated values.
 
         Raises
         ------
@@ -110,7 +108,7 @@ class ANTsWarper:
             run_ext_cmd(name="ResampleImage", cmd=resample_image_cmd)
 
             # Create a tempfile for warped output
-            apply_transforms_out_path = element_tempdir / "output.nii.gz"
+            apply_transforms_out_path = element_tempdir / "warped_data.nii.gz"
             # Set antsApplyTransforms command
             apply_transforms_cmd = [
                 "antsApplyTransforms",
@@ -126,14 +124,59 @@ class ANTsWarper:
             # Call antsApplyTransforms
             run_ext_cmd(name="antsApplyTransforms", cmd=apply_transforms_cmd)
 
-            # Load nifti
-            input["data"] = nib.load(apply_transforms_out_path)
-            # Save resampled reference path
-            input["reference"] = {"path": resample_image_out_path}
-            # Keep pre-warp space for further operations
-            input["prewarp_space"] = input["space"]
-            # Use reference input's space as warped input's space
-            input["space"] = extra_input["T1w"]["space"]
+            logger.debug("Updating warped data")
+            input.update(
+                {
+                    # Update path to sync with "data"
+                    "path": apply_transforms_out_path,
+                    # Load nifti
+                    "data": nib.load(apply_transforms_out_path),
+                    # Use reference input's space as warped input's space
+                    "space": extra_input["T1w"]["space"],
+                    # Save resampled reference path
+                    "reference": {"path": resample_image_out_path},
+                    # Keep pre-warp space for further operations
+                    "prewarp_space": input["space"],
+                }
+            )
+
+            # Check for data type's mask and warp if found
+            if input.get("mask") is not None:
+                # Create a tempfile for warped mask output
+                apply_transforms_mask_out_path = (
+                    element_tempdir / "warped_mask.nii.gz"
+                )
+                # Set antsApplyTransforms command
+                apply_transforms_mask_cmd = [
+                    "antsApplyTransforms",
+                    "-d 3",
+                    "-e 3",
+                    "-n 'GenericLabel[NearestNeighbor]'",
+                    f"-i {input['mask']['path'].resolve()}",
+                    # use resampled reference
+                    f"-r {input['reference']['path'].resolve()}",
+                    f"-t {warp_file_path.resolve()}",
+                    f"-o {apply_transforms_mask_out_path.resolve()}",
+                ]
+                # Call antsApplyTransforms
+                run_ext_cmd(
+                    name="antsApplyTransforms", cmd=apply_transforms_mask_cmd
+                )
+
+                logger.debug("Updating warped mask data")
+                input.update(
+                    {
+                        "mask": {
+                            # Update path to sync with "data"
+                            "path": apply_transforms_mask_out_path,
+                            # Load nifti
+                            "data": nib.load(apply_transforms_mask_out_path),
+                            # Use reference input's space as warped input
+                            # mask's space
+                            "space": extra_input["T1w"]["space"],
+                        }
+                    }
+                )
 
         # Template space warping
         else:
@@ -149,16 +192,15 @@ class ANTsWarper:
                 target_data=input,
                 extra_input=None,
             )
-
-            # Create component-scoped tempdir
-            tempdir = WorkDirManager().get_tempdir(prefix="ants_warper")
             # Save template
-            template_space_img_path = tempdir / f"{reference}_T1w.nii.gz"
+            template_space_img_path = (
+                element_tempdir / f"{reference}_T1w.nii.gz"
+            )
             nib.save(template_space_img, template_space_img_path)
 
             # Create a tempfile for warped output
             warped_output_path = element_tempdir / (
-                f"data_warped_from_{input['space']}_to_" f"{reference}.nii.gz"
+                f"warped_data_from_{input['space']}_to_{reference}.nii.gz"
             )
 
             # Set antsApplyTransforms command
@@ -175,14 +217,58 @@ class ANTsWarper:
             # Call antsApplyTransforms
             run_ext_cmd(name="antsApplyTransforms", cmd=apply_transforms_cmd)
 
-            # Delete tempdir
-            WorkDirManager().delete_tempdir(tempdir)
+            logger.debug("Updating warped data")
+            input.update(
+                {
+                    # Update path to sync with "data"
+                    "path": warped_output_path,
+                    # Load nifti
+                    "data": nib.load(warped_output_path),
+                    # Update warped input's space
+                    "space": reference,
+                    # Save reference path
+                    "reference": {"path": template_space_img_path},
+                    # Keep pre-warp space for further operations
+                    "prewarp_space": input["space"],
+                }
+            )
+
+            # Check for data type's mask and warp if found
+            if input.get("mask") is not None:
+                # Create a tempfile for warped mask output
+                apply_transforms_mask_out_path = element_tempdir / (
+                    f"warped_mask_from_{input['space']}_to_"
+                    f"{reference}.nii.gz"
+                )
+                # Set antsApplyTransforms command
+                apply_transforms_mask_cmd = [
+                    "antsApplyTransforms",
+                    "-d 3",
+                    "-e 3",
+                    "-n 'GenericLabel[NearestNeighbor]'",
+                    f"-i {input['mask']['path'].resolve()}",
+                    # use resampled reference
+                    f"-r {input['reference']['path'].resolve()}",
+                    f"-t {xfm_file_path.resolve()}",
+                    f"-o {apply_transforms_mask_out_path.resolve()}",
+                ]
+                # Call antsApplyTransforms
+                run_ext_cmd(
+                    name="antsApplyTransforms", cmd=apply_transforms_mask_cmd
+                )
 
-            # Modify target data
-            input["data"] = nib.load(warped_output_path)
-            # Keep pre-warp space for further operations
-            input["prewarp_space"] = input["space"]
-            # Update warped input's space
-            input["space"] = reference
+                logger.debug("Updating warped mask data")
+                input.update(
+                    {
+                        "mask": {
+                            # Update path to sync with "data"
+                            "path": apply_transforms_mask_out_path,
+                            # Load nifti
+                            "data": nib.load(apply_transforms_mask_out_path),
+                            # Update warped input mask's space
+                            "space": reference,
+                        }
+                    }
+                )
 
         return input