================= ======================== ============================================================================================================================================================================================================================================================== ========================================== =================================================================================================================================================================
Key               Subkey                   Description                                                                                                                                                                                                                                                    Default                                    Options                                                                                                                                                          
================= ======================== ============================================================================================================================================================================================================================================================== ========================================== =================================================================================================================================================================
General           cross_validation         Determine whether a cross validation will be performed or not. Obsolete, will be removed.                                                                                                                                                                      True                                       True, False                                                                                                                                                      
                  Segmentix                Determine whether to use Segmentix tool for segmentation preprocessing.                                                                                                                                                                                        False                                      True, False                                                                                                                                                      
                  FeatureCalculator        Specifies which feature calculation tool should be used.                                                                                                                                                                                                       predict/CalcFeatures:1.0                   predict/CalcFeatures:1.0, pyradiomics/CF_pyradiomics:1.0, your own tool reference                                                                                
                  Preprocessing            Specifies which tool will be used for image preprocessing.                                                                                                                                                                                                     worc/PreProcess:1.0                        worc/PreProcess:1.0, your own tool reference                                                                                                                     
                  RegistrationNode         Specifies which tool will be used for image registration.                                                                                                                                                                                                      'elastix4.8/Elastix:4.8'                   'elastix4.8/Elastix:4.8', your own tool reference                                                                                                                
                  TransformationNode       Specifies which tool will be used for applying image transformations.                                                                                                                                                                                          'elastix4.8/Transformix:4.8'               'elastix4.8/Transformix:4.8', your own tool reference                                                                                                            
                  Joblib_ncores            Number of cores to be used by joblib for multicore processing.                                                                                                                                                                                                 4                                          Integer > 0                                                                                                                                                      
                  Joblib_backend           Type of backend to be used by joblib for multicore processing.                                                                                                                                                                                                 multiprocessing                            multiprocessing, threading                                                                                                                                       
                  tempsave                 Determines whether after every cross validation iteration the result will be saved, in addition to the result after all iterations. Especially useful for debugging.                                                                                           False                                      True, False                                                                                                                                                      
Segmentix         mask                     If a mask is supplied, should the mask be subtracted from the contour or multiplied.                                                                                                                                                                           subtract                                   subtract, multiply                                                                                                                                               
                  segtype                  If Ring, then a ring around the segmentation will be used as contour.                                                                                                                                                                                          None                                       None, Ring                                                                                                                                                       
                  segradius                Define the radius of the ring used if segtype is Ring.                                                                                                                                                                                                         5                                          Integer > 0                                                                                                                                                      
                  N_blobs                  How many of the largest blobs are extracted from the segmentation. If None, no blob extraction is used.                                                                                                                                                        1                                          Integer > 0                                                                                                                                                      
                  fillholes                Determines whether hole filling will be used.                                                                                                                                                                                                                  False                                      True, False                                                                                                                                                      
Normalize         ROI                      If a mask is supplied and this is set to True, normalize image based on supplied ROI. Otherwise, the full image is used for normalization using the SimpleITK Normalize function. Lastly, setting this to False will result in no normalization being applied. Full                                       True, False, Full                                                                                                                                                
                  Method                   Method used for normalization if ROI is supplied. Currently, z-scoring or using the minimum and median of the ROI can be used.                                                                                                                                 z_score                                    z_score, minmed                                                                                                                                                  
ImageFeatures     shape                    Determine whether orientation features are computed or not.                                                                                                                                                                                                    True                                       True, False                                                                                                                                                      
                  histogram                Determine whether histogram features are computed or not.                                                                                                                                                                                                      True                                       True, False                                                                                                                                                      
                  orientation              Determine whether orientation features are computed or not.                                                                                                                                                                                                    True                                       True, False                                                                                                                                                      
                  texture_Gabor            Determine whether Gabor texture features are computed or not.                                                                                                                                                                                                  False                                      True, False                                                                                                                                                      
                  texture_LBP              Determine whether LBP texture features are computed or not.                                                                                                                                                                                                    True                                       True, False                                                                                                                                                      
                  texture_GLCM             Determine whether GLCM texture features are computed or not.                                                                                                                                                                                                   True                                       True, False                                                                                                                                                      
                  texture_GLCMMS           Determine whether GLCM Multislice texture features are computed or not.                                                                                                                                                                                        True                                       True, False                                                                                                                                                      
                  texture_GLRLM            Determine whether GLRLM texture features are computed or not.                                                                                                                                                                                                  True                                       True, False                                                                                                                                                      
                  texture_GLSZM            Determine whether GLSZM texture features are computed or not.                                                                                                                                                                                                  True                                       True, False                                                                                                                                                      
                  texture_NGTDM            Determine whether NGTDM texture features are computed or not.                                                                                                                                                                                                  True                                       True, False                                                                                                                                                      
                  coliage                  Determine whether coliage features are computed or not.                                                                                                                                                                                                        False                                      True, False                                                                                                                                                      
                  vessel                   Determine whether vessel features are computed or not.                                                                                                                                                                                                         False                                      True, False                                                                                                                                                      
                  log                      Determine whether LoG features are computed or not.                                                                                                                                                                                                            False                                      True, False                                                                                                                                                      
                  phase                    Determine whether local phase features are computed or not.                                                                                                                                                                                                    False                                      True, False                                                                                                                                                      
                  image_type               Modality of images supplied. Determines how the image is loaded.                                                                                                                                                                                               CT                                         CT                                                                                                                                                               
                  gabor_frequencies        Frequencies of Gabor filters used: can be a single float or a list.                                                                                                                                                                                            0.05, 0.2, 0.5                             Float(s)                                                                                                                                                         
                  gabor_angles             Angles of Gabor filters in degrees: can be a single integer or a list.                                                                                                                                                                                         0, 45, 90, 135                             Integer(s)                                                                                                                                                       
                  GLCM_angles              Angles used in GLCM computation in radians: can be a single float or a list.                                                                                                                                                                                   0, 0.79, 1.57, 2.36                        Float(s)                                                                                                                                                         
                  GLCM_levels              Number of grayscale levels used in discretization before GLCM computation.                                                                                                                                                                                     16                                         Integer > 0                                                                                                                                                      
                  GLCM_distances           Distance(s) used in GLCM computation in pixels: can be a single integer or a list.                                                                                                                                                                             1, 3                                       Integer(s) > 0                                                                                                                                                   
                  LBP_radius               Radii used for LBP computation: can be a single integer or a list.                                                                                                                                                                                             3, 8, 15                                   Integer(s) > 0                                                                                                                                                   
                  LBP_npoints              Number(s) of points used in LBP computation: can be a single integer or a list.                                                                                                                                                                                12, 24, 36                                 Integer(s) > 0                                                                                                                                                   
                  phase_minwavelength      Minimal wavelength in pixels used for phase features.                                                                                                                                                                                                          3                                          Integer > 0                                                                                                                                                      
                  phase_nscale             Number of scales used in phase feature computation.                                                                                                                                                                                                            5                                          Integer > 0                                                                                                                                                      
                  log_sigma                Standard deviation(s) in pixels used in log feature computation: can be a single integer or a list.                                                                                                                                                            1, 5, 10                                   Integer(s)                                                                                                                                                       
                  vessel_scale_range       Scale in pixels used for Frangi vessel filter. Given as a minimum and a maximum.                                                                                                                                                                               1, 10                                      Two integers: min and max.                                                                                                                                       
                  vessel_scale_step        Step size used to go from minimum to maximum scale on Frangi vessel filter.                                                                                                                                                                                    2                                          Integer > 0                                                                                                                                                      
                  vessel_radius            Radius to determine boundary of between inner part and edge in Frangi vessel filter.                                                                                                                                                                           5                                          Integer > 0                                                                                                                                                      
Featsel           Variance                 If True, exclude features which have a variance < 0.01. Based on ` sklearn <https://scikit-learn.org/stable/modules/generated/sklearn.feature_selection.VarianceThreshold.html/>`_.                                                                            True                                       Boolean(s)                                                                                                                                                       
                  GroupwiseSearch          Randomly select which feature groups to use. Parameters determined by the SelectFeatGroup config part, see below.                                                                                                                                              True                                       Boolean(s)                                                                                                                                                       
                  SelectFromModel          Select features by first training a LASSO model. The alpha for the LASSO model is randomly generated. See also `sklearn <https://scikit-learn.org/stable/modules/generated/sklearn.feature_selection.SelectFromModel.html/>`_.                                 False                                      Boolean(s)                                                                                                                                                       
                  UsePCA                   If True, Use Principle Component Analysis (PCA) to select features.                                                                                                                                                                                            False                                      Boolean(s)                                                                                                                                                       
                  PCAType                  Method to select number of components using PCA: Either the number of components that explains 95% of the variance, or use a fixed number of components.95variance                                                                                             95variance                                 Inteteger(s), 95variance                                                                                                                                         
                  StatisticalTestUse       If True, use statistical test to select features.                                                                                                                                                                                                              False                                      Boolean(s)                                                                                                                                                       
                  StatisticalTestMetric    Define the type of statistical test to be used.                                                                                                                                                                                                                ttest, Welch, Wilcoxon, MannWhitneyU       ttest, Welch, Wilcoxon, MannWhitneyU                                                                                                                             
                  StatisticalTestThreshold Specify a threshold for the p-value threshold used in the statistical test to select features. The first element defines the lower boundary, the other the upper boundary. Random sampling will occur between the boundaries.                                  -2, 1.5                                    Two Integers: loc and scale                                                                                                                                      
                  ReliefUse                If True, use Relief to select features.                                                                                                                                                                                                                        False                                      Boolean(s)                                                                                                                                                       
                  ReliefNN                 Min and max of number of nearest neighbors search range in Relief.                                                                                                                                                                                             2, 4                                       Two Integers: loc and scale                                                                                                                                      
                  ReliefSampleSize         Min and max of sample size search range in Relief.                                                                                                                                                                                                             1, 1                                       Two Integers: loc and scale                                                                                                                                      
                  ReliefDistanceP          Min and max of positive distance search range in Relief.                                                                                                                                                                                                       1, 3                                       Two Integers: loc and scale                                                                                                                                      
                  ReliefNumFeatures        Min and max of number of features that is selected search range in Relief.                                                                                                                                                                                     25, 200                                    Two Integers: loc and scale                                                                                                                                      
SelectFeatGroup   shape_features           If True, use shape features in model.                                                                                                                                                                                                                          True, False                                Boolean(s)                                                                                                                                                       
                  histogram_features       If True, use histogram features in model.                                                                                                                                                                                                                      True, False                                Boolean(s)                                                                                                                                                       
                  orientation_features     If True, use orientation features in model.                                                                                                                                                                                                                    True, False                                Boolean(s)                                                                                                                                                       
                  texture_Gabor_features   If True, use Gabor texture features in model.                                                                                                                                                                                                                  False                                      Boolean(s)                                                                                                                                                       
                  texture_GLCM_features    If True, use GLCM texture features in model.                                                                                                                                                                                                                   True, False                                Boolean(s)                                                                                                                                                       
                  texture_GLCMMS_features  If True, use GLCM Multislice texture features in model.                                                                                                                                                                                                        True, False                                Boolean(s)                                                                                                                                                       
                  texture_GLRLM_features   If True, use GLRLM texture features in model.                                                                                                                                                                                                                  True, False                                Boolean(s)                                                                                                                                                       
                  texture_GLSZM_features   If True, use GLSZM texture features in model.                                                                                                                                                                                                                  True, False                                Boolean(s)                                                                                                                                                       
                  texture_NGTDM_features   If True, use NGTDM texture features in model.                                                                                                                                                                                                                  True, False                                Boolean(s)                                                                                                                                                       
                  texture_LBP_features     If True, use LBP texture features in model.                                                                                                                                                                                                                    True, False                                Boolean(s)                                                                                                                                                       
                  patient_features         If True, use patient features in model.                                                                                                                                                                                                                        False                                      Boolean(s)                                                                                                                                                       
                  semantic_features        If True, use semantic features in model.                                                                                                                                                                                                                       False                                      Boolean(s)                                                                                                                                                       
                  coliage_features         If True, use coliage features in model.                                                                                                                                                                                                                        False                                      Boolean(s)                                                                                                                                                       
                  log_features             If True, use log features in model.                                                                                                                                                                                                                            False                                      Boolean(s)                                                                                                                                                       
                  vessel_features          If True, use vessel features in model.                                                                                                                                                                                                                         False                                      Boolean(s)                                                                                                                                                       
                  phase_features           If True, use phase features in model.                                                                                                                                                                                                                          False                                      Boolean(s)                                                                                                                                                       
Imputation        use                      If True, use feature imputation methods to replace NaN values. If False, all NaN features will be set to zero.                                                                                                                                                 False                                      Boolean(s)                                                                                                                                                       
                  strategy                 Method to be used for imputation.                                                                                                                                                                                                                              mean, median, most_frequent, constant, knn mean, median, most_frequent, constant, knn                                                                                                                       
                  n_neighbors              When using k-Nearest Neighbors (kNN) for feature imputation, determines the number of neighbors used for imputation. Can be a single integer or a list.                                                                                                        5, 5                                       Two Integers: loc and scale                                                                                                                                      
Classification    fastr                    Use fastr for the optimization gridsearch (recommended on clusters, default) or if set to False , joblib (recommended for PCs but not on Windows).                                                                                                             True                                       True, False                                                                                                                                                      
                  fastr_plugin             Name of execution plugin to be used. Default use the same as the self.fastr_plugin for the WORC object.                                                                                                                                                        LinearExecution                            Any `fastr execution plugin <https://fastr.readthedocs.io/en/develop/_autogen/fastr.reference.html#executionplugin-reference/>`_ .                               
                  classifiers              Select the estimator(s) to use. Most are implemented using `sklearn <https://scikit-learn.org/stable/>`_. For abbreviations, see above.                                                                                                                        SVM                                        SVM , SVR, SGD, SGDR, RF, LDA, QDA, ComplementND, GaussianNB, LR, RFR, Lasso, ElasticNet. All are estimators from `sklearn <https://scikit-learn.org/stable//>`_ 
                  max_iter                 Maximum number of iterations to use in training an estimator. Only for specific estimators, see `sklearn <https://scikit-learn.org/stable/>`_.                                                                                                                 100000                                     Integer                                                                                                                                                          
                  SVMKernel                When using a SVM, specify the kernel type.                                                                                                                                                                                                                     poly                                       poly, linear, rbf                                                                                                                                                
                  SVMC                     Range of the SVM slack parameter. We sample on a uniform log scale: the parameters specify the range of the exponent (a, a + b).                                                                                                                               0, 6                                       Two Integers: loc and scale                                                                                                                                      
                  SVMdegree                Range of the SVM polynomial degree when using a polynomial kernel. We sample on a uniform scale: the parameters specify the range (a, a + b).                                                                                                                  1, 6                                       Two Integers: loc and scale                                                                                                                                      
                  SVMcoef0                 Range of SVM homogeneity parameter. We sample on a uniform scale: the parameters specify the range (a, a + b).                                                                                                                                                 0, 1                                       Two Integers: loc and scale                                                                                                                                      
                  SVMgamma                 Range of the SVM gamma parameter. We sample on a uniform log scale: the parameters specify the range of the exponent (a, a + b)                                                                                                                                -5, 5                                      Two Integers: loc and scale                                                                                                                                      
                  RFn_estimators           Range of number of trees in a RF. We sample on a uniform scale: the parameters specify the range (a, a + b).                                                                                                                                                   10, 90                                     Two Integers: loc and scale                                                                                                                                      
                  RFmin_samples_split      Range of minimum number of samples required to split a branch in a RF. We sample on a uniform scale: the parameters specify the range (a, a + b).                                                                                                              2, 3                                       Two Integers: loc and scale                                                                                                                                      
                  RFmax_depth              Range of maximum depth of a RF. We sample on a uniform scale: the parameters specify the range (a, a + b).                                                                                                                                                     5, 5                                       Two Integers: loc and scale                                                                                                                                      
                  LRpenalty                Penalty term used in LR.                                                                                                                                                                                                                                       l2, l1                                     none, l2, l1                                                                                                                                                     
                  LRC                      Range of regularization strength in LR. We sample on a uniform scale: the parameters specify the range (a, a + b).                                                                                                                                             0.01, 1.0                                  Two Integers: loc and scale                                                                                                                                      
                  LDA_solver               Solver used in LDA.                                                                                                                                                                                                                                            svd, lsqr, eigen                           svd, lsqr, eigen                                                                                                                                                 
                  LDA_shrinkage            Range of the LDA shrinkage parameter. We sample on a uniform log scale: the parameters specify the range of the exponent (a, a + b).                                                                                                                           -5, 5                                      Two Integers: loc and scale                                                                                                                                      
                  QDA_reg_param            Range of the QDA regularization parameter. We sample on a uniform log scale: the parameters specify the range of the exponent (a, a + b).                                                                                                                      -5, 5                                      Two Integers: loc and scale                                                                                                                                      
                  ElasticNet_alpha         Range of the ElasticNet penalty parameter. We sample on a uniform log scale: the parameters specify the range of the exponent (a, a + b).                                                                                                                      -5, 5                                      Two Integers: loc and scale                                                                                                                                      
                  ElasticNet_l1_ratio      Range of l1 ratio in LR. We sample on a uniform scale: the parameters specify the range (a, a + b).                                                                                                                                                            0, 1                                       Two Integers: loc and scale                                                                                                                                      
                  SGD_alpha                Range of the SGD penalty parameter. We sample on a uniform log scale: the parameters specify the range of the exponent (a, a + b).                                                                                                                             -5, 5                                      Two Integers: loc and scale                                                                                                                                      
                  SGD_l1_ratio             Range of l1 ratio in SGD. We sample on a uniform scale: the parameters specify the range (a, a + b).                                                                                                                                                           0, 1                                       Two Integers: loc and scale                                                                                                                                      
                  SGD_loss                 hinge, Loss function of SG                                                                                                                                                                                                                                     hinge, squared_hinge, modified_huber       hinge, squared_hinge, modified_huber                                                                                                                             
                  SGD_penalty              Penalty term in SGD.                                                                                                                                                                                                                                           none, l2, l1                               none, l2, l1                                                                                                                                                     
                  CNB_alpha                Regularization strenght in ComplementNB. We sample on a uniform scale: the parameters specify the range (a, a + b)                                                                                                                                             0, 1                                       Two Integers: loc and scale                                                                                                                                      
CrossValidation   N_iterations             Number of times the data is split in training and test in the outer cross-validation.                                                                                                                                                                          100                                        Integer                                                                                                                                                          
                  test_size                The percentage of data to be used for testing.                                                                                                                                                                                                                 0.2                                        Float                                                                                                                                                            
Labels            label_names              The labels used from your label file for classification.                                                                                                                                                                                                       Label1, Label2                             String(s)                                                                                                                                                        
                  modus                    Determine whether multilabel or singlelabel classification or regression will be performed.                                                                                                                                                                    singlelabel                                singlelabel, multilabel                                                                                                                                          
                  url                      WIP                                                                                                                                                                                                                                                            WIP                                        Not Supported Yet                                                                                                                                                
                  projectID                WIP                                                                                                                                                                                                                                                            WIP                                        Not Supported Yet                                                                                                                                                
HyperOptimization scoring_method           Specify the optimization metric for your hyperparameter search.                                                                                                                                                                                                f1_weighted                                Any `sklearn metric <https://scikit-learn.org/stable/modules/model_evaluation.html#common-cases-predefined-values/>`_                                            
                  test_size                Size of test set in the hyperoptimization cross validation, given as a percentage of the whole dataset.                                                                                                                                                        0.15                                       Float                                                                                                                                                            
                  n_splits                                                                                                                                                                                                                                                                                5                                          5                                                                                                                                                                
                  N_iterations             Number of iterations used in the hyperparameter optimization. This corresponds to the number of samples drawn from the parameter grid.                                                                                                                         10000                                      Integer                                                                                                                                                          
                  n_jobspercore            Number of jobs assigned to a single core. Only used if fastr is set to true in the classfication.                                                                                                                                                              2000                                       Integer                                                                                                                                                          
                  maxlen                                                                                                                                                                                                                                                                                  100                                        100                                                                                                                                                              
                  ranking_score                                                                                                                                                                                                                                                                           test_score                                 test_score                                                                                                                                                       
FeatureScaling    scale_features           Determine whether to use feature scaling is.                                                                                                                                                                                                                   True                                       Boolean(s)                                                                                                                                                       
                  scaling_method           Determine the scaling method.                                                                                                                                                                                                                                  z_score                                    z_score, minmax                                                                                                                                                  
SampleProcessing  SMOTE                    Determine whether to use SMOTE oversampling, see also ` imbalanced learn <https://imbalanced-learn.readthedocs.io/en/stable/generated/imblearn.over_sampling.SMOTE.html/>`_.                                                                                   True                                       Boolean(s)                                                                                                                                                       
                  SMOTE_ratio              Determine the ratio of oversampling. If 1, the minority class will be oversampled to the same size as the majority class. We sample on a uniform scale: the parameters specify the range (a, a + b).                                                           1, 0                                       Two Integers: loc and scale                                                                                                                                      
                  SMOTE_neighbors          Number of neighbors used in SMOTE. This should be much smaller than the number of objects/patients you supply. We sample on a uniform scale: the parameters specify the range (a, a + b).                                                                      5, 15                                      Two Integers: loc and scale                                                                                                                                      
                  Oversampling             Determine whether to random oversampling.                                                                                                                                                                                                                      False                                      Boolean(s)                                                                                                                                                       
Ensemble          Use                      Determine whether to use ensembling or not. Either provide an integer to state how many estimators to include, or True, which will use the default ensembling method.                                                                                          1                                          Boolean or Integer                                                                                                                                               
Bootstrap         Use                                                                                                                                                                                                                                                                                     False                                      False                                                                                                                                                            
                  N_iterations                                                                                                                                                                                                                                                                            1000                                       1000                                                                                                                                                             
================= ======================== ============================================================================================================================================================================================================================================================== ========================================== =================================================================================================================================================================