WORC Package

WORC Package

WORC Module

class WORC.WORC.Tools[source]

Bases: object

Create other pipelines besides the default radiomics executions.

Currently includes: 1. Registration pipeline 2. Evaluation pipeline 3. Slicer pipeline, to create pngs of middle slice of images.

__dict__ = mappingproxy({'__module__': 'WORC.WORC', '__doc__': '\n    Create other pipelines besides the default radiomics executions.\n\n    Currently includes:\n    1. Registration pipeline\n    2. Evaluation pipeline\n    3. Slicer pipeline, to create pngs of middle slice of images.\n    ', '__init__': <function Tools.__init__>, '__dict__': <attribute '__dict__' of 'Tools' objects>, '__weakref__': <attribute '__weakref__' of 'Tools' objects>, '__annotations__': {}})
__init__()[source]

Initialize object with all pipelines.

__module__ = 'WORC.WORC'
__weakref__

list of weak references to the object (if defined)

class WORC.WORC.WORC(name='test')[source]

Bases: object

Workflow for Optimal Radiomics Classification.

A Workflow for Optimal Radiomics Classification (WORC) object that serves as a pipeline spawner and manager for optimizating radiomics studies. Depending on the attributes set, the object will spawn an appropriate pipeline and manage it.

Note that many attributes are lists and can therefore contain multiple instances. For example, when providing two sequences per patient, the “images” list contains two items. The type of items in the lists is described below.

All objects that serve as source for your network, i.e. refer to actual files to be used, should be formatted as fastr sources suited for one of the fastr plugings, see also http://fastr.readthedocs.io/en/stable/fastr.reference.html#ioplugin-reference The objects should be lists of these fastr sources or dictionaries with the sample ID’s, e.g.

images_train = [{‘Patient001’: vfs://input/CT001.nii.gz,

‘Patient002’: vfs://input/CT002.nii.gz},

{‘Patient001’: vfs://input/MR001.nii.gz,

‘Patient002’: vfs://input/MR002.nii.gz}]

Attributes

name: String, default ‘WORC’

name of the network.

configs: list, required

Configuration parameters, either ConfigParser objects created through the defaultconfig function or paths of config .ini files. (list, required)

labels: list, required

Paths to files containing patient labels (.txt files).

network: automatically generated

The FASTR network generated through the “build” function.

images: list, optional

Paths refering to the images used for Radiomics computation. Images should be of the ITK Image type.

segmentations: list, optional

Paths refering to the segmentations used for Radiomics computation. Segmentations should be of the ITK Image type.

semantics: semantic features per image type (list, optional)

masks: state which pixels of images are valid (list, optional)

features: input Radiomics features for classification (list, optional)

metadata: DICOM headers belonging to images (list, optional)

Elastix_Para: parameter files for Elastix (list, optional)

fastr_plugin: plugin to use for FASTR execution

fastr_tempdir: temporary directory to use for FASTR execution

additions: additional inputs for your network (dict, optional)

source_data: data to use as sources for FASTR (dict)

sink_data: data to use as sinks for FASTR (dict)

CopyMetadata: Boolean, default True

when using elastix, copy metadata from image to segmentation or not

__dict__ = mappingproxy({'__module__': 'WORC.WORC', '__doc__': 'Workflow for Optimal Radiomics Classification.\n\n    A Workflow for Optimal Radiomics Classification (WORC) object that\n    serves as a pipeline spawner and manager for optimizating radiomics\n    studies. Depending on the attributes set, the object will spawn an\n    appropriate pipeline and manage it.\n\n    Note that many attributes are lists and can therefore contain multiple\n    instances. For example, when providing two sequences per patient,\n    the "images" list contains two items. The type of items in the lists\n    is described below.\n\n    All objects that serve as source for your network, i.e. refer to\n    actual files to be used, should be formatted as fastr sources suited for\n    one of the fastr plugings, see also\n    http://fastr.readthedocs.io/en/stable/fastr.reference.html#ioplugin-reference\n    The objects should be lists of these fastr sources or dictionaries with the\n    sample ID\'s, e.g.\n\n    images_train = [{\'Patient001\': vfs://input/CT001.nii.gz,\n                     \'Patient002\': vfs://input/CT002.nii.gz},\n                    {\'Patient001\': vfs://input/MR001.nii.gz,\n                     \'Patient002\': vfs://input/MR002.nii.gz}]\n\n    Attributes\n    ------------------\n        name: String, default \'WORC\'\n            name of the network.\n\n        configs: list, required\n            Configuration parameters, either ConfigParser objects\n            created through the defaultconfig function or paths of config .ini\n            files. (list, required)\n\n        labels: list, required\n            Paths to files containing patient labels (.txt files).\n\n        network: automatically generated\n            The FASTR network generated through the "build" function.\n\n        images: list, optional\n            Paths refering to the images used for Radiomics computation. Images\n            should be of the ITK Image type.\n\n        segmentations: list, optional\n            Paths refering to the segmentations used for Radiomics computation.\n            Segmentations should be of the ITK Image type.\n\n        semantics: semantic features per image type (list, optional)\n\n        masks: state which pixels of images are valid (list, optional)\n\n        features: input Radiomics features for classification (list, optional)\n\n        metadata: DICOM headers belonging to images (list, optional)\n\n        Elastix_Para: parameter files for Elastix (list, optional)\n\n        fastr_plugin: plugin to use for FASTR execution\n\n        fastr_tempdir: temporary directory to use for FASTR execution\n\n        additions: additional inputs for your network (dict, optional)\n\n        source_data: data to use as sources for FASTR (dict)\n\n        sink_data: data to use as sinks for FASTR (dict)\n\n        CopyMetadata: Boolean, default True\n            when using elastix, copy metadata from image to segmentation or not\n\n    ', '__init__': <function WORC.__init__>, 'defaultconfig': <function WORC.defaultconfig>, 'add_tools': <function WORC.add_tools>, 'build': <function WORC.build>, 'build_training': <function WORC.build_training>, 'build_inference': <function WORC.build_inference>, 'add_fingerprinter': <function WORC.add_fingerprinter>, 'add_ComBat': <function WORC.add_ComBat>, 'add_preprocessing': <function WORC.add_preprocessing>, 'add_feature_calculator': <function WORC.add_feature_calculator>, 'add_elastix_sourcesandsinks': <function WORC.add_elastix_sourcesandsinks>, 'add_elastix': <function WORC.add_elastix>, 'add_segmentix': <function WORC.add_segmentix>, 'set': <function WORC.set>, 'execute': <function WORC.execute>, 'add_evaluation': <function WORC.add_evaluation>, 'save_config': <function WORC.save_config>, '__dict__': <attribute '__dict__' of 'WORC' objects>, '__weakref__': <attribute '__weakref__' of 'WORC' objects>, '__annotations__': {}})
__init__(name='test')[source]

Initialize WORC object.

Set the initial variables all to None, except for some defaults.

Arguments:

name: name of the nework (string, optional)

__module__ = 'WORC.WORC'
__weakref__

list of weak references to the object (if defined)

add_ComBat()[source]

Add ComBat harmonization to the network.

Note: applied on all objects, not in a train-test or cross-val setting.

add_elastix(label, nmod)[source]

Add image registration through elastix to network.

add_elastix_sourcesandsinks()[source]

Add sources and sinks required for image registration.

add_evaluation(label_type, modus='binary_classification')[source]

Add branch for evaluation of performance to network.

Note: should be done after build, before set: WORC.build() WORC.add_evaluation(label_type) WORC.set() WORC.execute()

add_feature_calculator(calcfeat_node, label, nmod)[source]

Add a feature calculation node to the network.

add_fingerprinter(id, type, config_source)[source]

Add WORC Fingerprinter to the network.

Note: applied per imaging sequence, or per feature file if no images are present.

add_preprocessing(preprocess_node, label, nmod)[source]

Add nodes required for preprocessing of images.

add_segmentix(label, nmod)[source]

Add segmentix to the network.

add_tools()[source]

Add several tools to the WORC object.

build(buildtype='training')[source]

Build the network based on the given attributes.

Parameters

buildtype: string, default ‘training’

Specify the WORC execution type. - inference: use if you have a trained classifier and want to

train it on some new images.

  • training: use if you want to train a classifier from a dataset.

build_inference()[source]

Build a network to test an already trained model on a test dataset based on the given attributes.

build_training()[source]

Build the training network based on the given attributes.

defaultconfig()[source]

Generate a configparser object holding all default configuration values.

Returns:

config: configparser configuration file

execute()[source]

Execute the network through the fastr.network.execute command.

save_config()[source]

Save the config files to physical files and add to network.

set()[source]

Set the FASTR source and sink data based on the given attributes.

addexceptions Module

This module contains all WORC-related Exceptions

exception WORC.addexceptions.WORCAssertionError[source]

Bases: WORCError, AssertionError

AssertionError in the WORC system

__module__ = 'WORC.addexceptions'
exception WORC.addexceptions.WORCError[source]

Bases: Exception

This is the base class for all WORC related exceptions. Catching this class of exceptions should ensure a proper execution of WORC.

__module__ = 'WORC.addexceptions'
__weakref__

list of weak references to the object (if defined)

exception WORC.addexceptions.WORCIOError[source]

Bases: WORCError, OSError

IOError in WORC

__module__ = 'WORC.addexceptions'
__weakref__

list of weak references to the object (if defined)

exception WORC.addexceptions.WORCIndexError[source]

Bases: WORCError, IndexError

IndexError in the WORC system

__module__ = 'WORC.addexceptions'
exception WORC.addexceptions.WORCKeyError[source]

Bases: WORCError, KeyError

KeyError in the WORC system

__module__ = 'WORC.addexceptions'
exception WORC.addexceptions.WORCNotImplementedError[source]

Bases: WORCError, NotImplementedError

This function/method has not been implemented on purpose (e.g. should be overwritten in a sub-class)

__module__ = 'WORC.addexceptions'
exception WORC.addexceptions.WORCTypeError[source]

Bases: WORCError, TypeError

TypeError in the WORC system

__module__ = 'WORC.addexceptions'
exception WORC.addexceptions.WORCValueError[source]

Bases: WORCError, ValueError

ValueError in the WORC system

__module__ = 'WORC.addexceptions'

Subpackages