A python package for DICOM to NifTi and NifTi to DICOM-SEG and GSPS conversion
Project description
Nekton
A python package for DICOM to NifTi and NifTi to DICOM-SEG and GSPS conversion
SETUP
The python package is available for use on PyPI. It can be setup simply via pip
pip install nekton
To the check the setup, simply check the version number of the nekton
package by
python -c 'import nekton; print(nekton.__version__)'
DICOM to NifTi
The DICOM to NifTi conversion in the package is based on a wrapper around the dcm2niix software.
Usage
from nekton.dcm2nii import Dcm2Nii
converter = Dcm2Nii()
converted_files = converter.run(dicom_directory='/test_files/CT5N', out_directory='/test_files/CT5N', name='Test')
# Converted 5 DCM to Nifti; Output stored @ /test_files/CT5N
print(converted_files)
# ['/test_files/CT5N/Test_SmartScore_-_Gated_0.5_sec_20010101000000_5.nii.gz']
Parameters converter.run
:
dicom_directory (Path)
: path to directory with Dicomsdicom_directory (Path, optional)
: directory to store the output niftiname (str, optional)
: Name to be given to the output file. Defaults to "".
Returns:
List[Path]
: output list of Nifti files
Notes
- The renaming functionality retains the suffixes from the original program.
- The BIDS sidecar json is retained as well.
NifTi to DICOM-SEG
The NifTi to DICOM-SEG within nekton converts incoming segmentation NifTi to DICOM-SEG. The matching of the segmentation index to a text label is
done via json file using the schema suggested by dcmqi
. The json can be generated using the gui also an example can be seen here.
Currently, nekton
supports creation of multiclass DICOM-SEG of two types-
- single layer DICOM-SEG, where each non-empty slice has an individual file
- multi layer DICOM-SEG, where all the n slices are rolled into a single file
Usage
- NifTi to single layer DICOM-SEG
from nekton.nii2dcm import Nii2DcmSeg
import glob
converter = Nii2DcmSeg()
path_dcms = [path for path in glob.glob(dir_dcms)]
path_mapping = "mapping.json"
path_seg_nifti = "CT5N_segmentation.nii.gz"
dcmsegs = converter_dcmseg.multiclass_converter(
segfile = path_seg_nifti, segMapping= path_mapping, dcmfiles =path_dcms, multiLayer=False
)
print (len(dcmsegs))
# 3
- NifTi to multi layer DICOM-SEG
from nekton.nii2dcm import Nii2DcmSeg
import glob
converter = Nii2DcmSeg()
path_dcms = [path for path in glob.glob(dir_dcms)]
path_mapping = "mapping.json"
path_seg_nifti = "CT5N_segmentation.nii.gz"
dcmsegs = converter.multiclass_converter(
segfile = path_seg_nifti, segMapping= path_mapping, dcmfiles =path_dcms, multiLayer=True
)
print (len(dcmsegs))
# 1
Parameters converter.multiclass_converter
:
segfile (Path)
: path to the nifti segmentation filesegMapping (Path)
: path to the dcmqii format segmentation mapping jsondcmfiles (List[Path])
: list of paths of all the source dicom filesmultiLayer (bool, optional)
: create a single multilayer dicomseg. Defaults to False.
Returns:
List[Path]
: list of paths of all generated dicomseg files
Notes
- Multilabel NifTi(in the form of a NifTi file for a single label) to DICOM-SEG is under development.
NifTi to GSPS
This feature will be available in a future release of the nekton
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file nekton-0.2.5.tar.gz
.
File metadata
- Download URL: nekton-0.2.5.tar.gz
- Upload date:
- Size: 264.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: poetry/1.2.1 CPython/3.9.14 Linux/5.15.0-48-generic
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 1db055245fb7bc4a7bb0134a776016690a8125ae584490ea9a0827941563ac5d |
|
MD5 | f921c9c5d7064d648018d9bad92a7581 |
|
BLAKE2b-256 | dbdd2b0585a9683e95df7f7b6c038e8e9e157a926260234433692dd055305deb |
File details
Details for the file nekton-0.2.5-py3-none-any.whl
.
File metadata
- Download URL: nekton-0.2.5-py3-none-any.whl
- Upload date:
- Size: 264.9 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: poetry/1.2.1 CPython/3.9.14 Linux/5.15.0-48-generic
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | ea2d7ee77f7e46250b57bc96fb072cefbd31520e00e77970991794417e9306f6 |
|
MD5 | b1633ccdba3b3fc44513f836649abe06 |
|
BLAKE2b-256 | fbf974026b699eb56f0e828317727fcfbb1c53ffbe27b2be69efccbb1735ff85 |