platipy.dicom.io package#

Submodules#

platipy.dicom.io.crawl module#

platipy.dicom.io.crawl.fix_missing_data(contour_data_list)#

Fixes missing points in contouring using simple linear interpolation

Parameters:

contour_data_list (list) – The contour data for each slice

Returns:

Interpolated contour data

Return type:

contour_data (numpy array)

platipy.dicom.io.crawl.flatten(itr)#
platipy.dicom.io.crawl.get_dicom_info_from_description(dicom_object, return_extra=False, sop_class_name='UNKNOWN')#

Attempts to return some information from a DICOM This is typically used for naming converted NIFTI files

Parameters:

  • dicom_object (pydicom.dataset.FileDataset) – The DICOM object

  • return_extra (bool, optional) – return information that is usually not required

Returns:

Some extracted information

Return type:

info (str)

platipy.dicom.io.crawl.get_suv_bw_scale_factor(ds)#
platipy.dicom.io.crawl.process_dicom_directory(dicom_directory, parent_sorting_field='PatientName', output_image_name_format='{parent_sorting_data}_{study_uid_index}_{Modality}_{image_desc}_{SeriesNumber}', output_structure_name_format='{parent_sorting_data}_{study_uid_index}_{Modality}_{structure_name}', output_dose_name_format='{parent_sorting_data}_{study_uid_index}_{DoseSummationType}', return_extra=True, output_directory='./', output_file_suffix='.nii.gz', overwrite_existing_files=False, write_to_disk=True, verbose=False, initial_sop_class_name_default='UNKNOWN')#
platipy.dicom.io.crawl.process_dicom_file_list(dicom_file_list, parent_sorting_field='PatientName', verbose=False)#

Organise the DICOM files by the series UID

platipy.dicom.io.crawl.process_dicom_series(dicom_series_dict, series_uid, parent_sorting_field='PatientName', return_extra=True, individual_file=False, initial_sop_class_name_default='UNKNOWN')#
platipy.dicom.io.crawl.safe_sort_dicom_image_list(dicom_image_list)#

Sorts a list of DICOM image files based on a DICOM tag value. This is a much safer method than reading SliceLocation. It takes mandatory DICOM fields (Image Position [Patient]) and (Image Orientation [Patient]). The list of DICOM files is sorted by projecting the image position onto the axis normal to the place defined by the image orientation.

This accounts for differences in patient position (e.g. HFS/FFS).

Parameters:

dicom_image_list (list) – [description]

platipy.dicom.io.crawl.transform_point_set_from_dicom_struct(image, dicom_struct, spacing_override=False)#

This function is used to generate a binary mask from a set of vertices. This allows us to convert from DICOM-RTStruct format to any imaging format.

Parameters:

  • image ([SimpleITK.Image]) – The image, used to copy imaging information (e.g. resolution, spacing)

  • dicom_struct ([pydicom.Dataset]) – The DICOM-RTStruct file

  • spacing_override (bool | tuple, optional) – Overwrite the spacing. Set with (axial_spacing, coronal_spacing, sagittal spacing). Defaults to False.

Returns:

final_struct_name_sequence, structure_list

Return type:

list, list

platipy.dicom.io.crawl.write_output_data_to_disk(output_data_dict, output_directory='./', output_file_suffix='.nii.gz', overwrite_existing_files=False)#

Write output to disk

platipy.dicom.io.nifti_to_rtstruct module#

platipy.dicom.io.nifti_to_rtstruct.convert_nifti(dcm_path, mask_input, output_file, color_map=<matplotlib.colors.LinearSegmentedColormap object>)#

Convert a set of masks to a DICOM RTStruct object.

This function now utilises the rt-utils package: https://github.com/qurit/rt-utils We keep this function in here for compatibility

Parameters:

  • dcm_path (str|pathlib.Path) – Path to the reference DICOM series

  • mask_input (dict|list) – A dictionary containing the name as key and image as value. Or a list of string with comma separated name and mask paths (name,path)

  • output_file (str|pathlib.Path) – The path to the file to write the RTStruct

  • color_map (matplotlib.colors.Colormap, optional) – Colormap to use for output. Defaults to matplotlib.colormaps.get_cmap(“rainbow”).

platipy.dicom.io.nifti_to_series module#

platipy.dicom.io.nifti_to_series.convert_nifti_to_dicom_series(image, reference_dcm, tag_overrides=[], output_directory='.')#

Converts a Nifti image to a Dicom image series

Parameters:

  • image (sitk.Image) – A SimpleITK image object to convert

  • reference_dcm (str) – A directory path containing a reference Dicom series to use

  • tag_overrides (list, optional) – A list of tags to override containing tuples of (key, value). Defaults to [].

  • output_directory (str, optional) – The directory in which to place the generated Dicom files. Defaults to “.”.

platipy.dicom.io.rtstruct_to_nifti module#

platipy.dicom.io.rtstruct_to_nifti.convert_rtstruct(dcm_img, dcm_rt_file, prefix='Struct_', output_dir='.', output_img=None, spacing=None, replace_slashes_with='')#

Convert a DICOM RTSTRUCT to NIFTI masks.

The masks are stored as NIFTI files in the output directory

Parameters:

  • dcm_img (str|pathlib.Path) – Path to the reference DICOM image series

  • dcm_rt_file (str|pathlib.Path) – Path to the DICOM RTSTRUCT file

  • prefix (str, optional) – The prefix to give the output files. Defaults to “Struct_”.

  • output_dir (str|pathlib.Path, optional) – Path to the output directory. Defaults to “.”.

  • output_img (str|pathlib.Path, optional) – If set, write the reference image to this file as in NIFTI format. Defaults to None.

  • spacing (list, optional) – Values of image spacing to override. Defaults to None.

  • replace_slashes_with (str, optional) – String to replace “/” and “” with. Set to None disable replacement of slashes. Defaults to “”.

platipy.dicom.io.rtstruct_to_nifti.fix_missing_data(contour_data)#

Fixed a set of contour data if there are values missing

Parameters:

contour_data (pydicom.Sequence) – The contour sequence from the DICOM object

Returns:

The array of contour data with missing values fixed

Return type:

np.array

platipy.dicom.io.rtstruct_to_nifti.read_dicom_image(dicom_path)#

Read a DICOM image series

Parameters:

dicom_path (str|pathlib.Path) – Path to the DICOM series to read

Returns:

The image as a SimpleITK Image

Return type:

sitk.Image

platipy.dicom.io.rtstruct_to_nifti.read_dicom_struct_file(filename)#

Read a DICOM RTSTRUCT file

Parameters:

filename (str|pathlib.Path) – Path to the RTSTRUCT to read

Returns:

The RTSTRUCT as a DICOM Dataset

Return type:

pydicom.Dataset

platipy.dicom.io.rtstruct_to_nifti.transform_point_set_from_dicom_struct(dicom_image, dicom_struct, spacing_override=None)#

Converts a set of points from a DICOM RTSTRUCT into a mask array

Parameters:

  • dicom_image (sitk.Image) – The reference image

  • dicom_struct (pydicom.Dataset) – The DICOM RTSTRUCT

  • spacing_override (list) – The spacing to override. Defaults to None

Returns:

Returns a list of masks and a list of structure names

Return type:

tuple

Module contents#