[Parcellation] Generate segmentation scores

Generate segmentation scores (precision, recall, F1) for a given parcellation based on a reference.

Parameters

input_type: OpenChoice ( input )

This parameter allows to change the database type of the input segmentation. It helps to automatically fill the process with the corresponding masks and reference.

input_segmentation: P:EM Parcellation ( input )

The evaluated segmentation.

input_mask: P:Skull Stripping Mask ( optional, input )

A mask in which scores should be computed. If a skull-stripping mask was used prior to the automated segmentation, it allows to discard voxels outisde this mask.

input_reference: P:Reference Parcellation ( input )

Tee ground truth segmentation.

input_reference_mask: P:Reference Parcellation Mask ( optional, input )

A mask in which to compute segmentation scores. If the reference segmentation does not cover the entire volume (if only a few section were selected for example), it allows to only use voxels which have an actual ground truth.

input_hierarchy: P:Atlas Labels Hierarchy ( input )

Hierarchy linking class values to regions. It also allows to compute classification scores in a hierarchical manner, by aggregating regions.

subject: String ( optional, input )

Subject name or ID. It will be stored in the output CSV.

analysis: ListOf( String ) ( optional, input )

Analysis name. It will be stored in the output CSV. Allows to keep track of parameters or to compare different algorithms.

output_directory: Directory ( optional, input )

Directory to write the output CSV.

output_csv: CSV file ( output )

Output table. One score per label and per hierarchy node are computed, plus three averaged scores (micro, macro, weighted).

Technical information

Toolbox : Primatologist

User level : 0

Identifier : segmentationScores

File name : brainvisa/toolboxes/primatologist/processes/tools/segmentationScores.py

Supported file formats :

input_segmentation :

gz compressed NIFTI-1 image, Aperio svs, BMP image, DICOM image, Directory, ECAT i image, ECAT v image, FDF image, FreesurferMGH, FreesurferMGZ, GIF image, GIS image, Hamamatsu ndpi, Hamamatsu vms, Hamamatsu vmu, JPEG image, Leica scn, MINC image, NIFTI-1 image, PBM image, PGM image, PNG image, PPM image, SPM image, Sakura svslide, TIFF image, TIFF image, TIFF(.tif) image, TIFF(.tif) image, VIDA image, Ventana bif, XBM image, XPM image, Zeiss czi, gz compressed MINC image, gz compressed NIFTI-1 image

input_mask :

gz compressed NIFTI-1 image, Aperio svs, BMP image, DICOM image, Directory, ECAT i image, ECAT v image, FDF image, FreesurferMGH, FreesurferMGZ, GIF image, GIS image, Hamamatsu ndpi, Hamamatsu vms, Hamamatsu vmu, JPEG image, Leica scn, MINC image, NIFTI-1 image, PBM image, PGM image, PNG image, PPM image, SPM image, Sakura svslide, TIFF image, TIFF image, TIFF(.tif) image, TIFF(.tif) image, VIDA image, Ventana bif, XBM image, XPM image, Zeiss czi, gz compressed MINC image, gz compressed NIFTI-1 image

input_reference :

gz compressed NIFTI-1 image, Aperio svs, BMP image, DICOM image, Directory, ECAT i image, ECAT v image, FDF image, FreesurferMGH, FreesurferMGZ, GIF image, GIS image, Hamamatsu ndpi, Hamamatsu vms, Hamamatsu vmu, JPEG image, Leica scn, MINC image, NIFTI-1 image, PBM image, PGM image, PNG image, PPM image, SPM image, Sakura svslide, TIFF image, TIFF image, TIFF(.tif) image, TIFF(.tif) image, VIDA image, Ventana bif, XBM image, XPM image, Zeiss czi, gz compressed MINC image, gz compressed NIFTI-1 image

input_reference_mask :

gz compressed NIFTI-1 image, Aperio svs, BMP image, DICOM image, Directory, ECAT i image, ECAT v image, FDF image, FreesurferMGH, FreesurferMGZ, GIF image, GIS image, Hamamatsu ndpi, Hamamatsu vms, Hamamatsu vmu, JPEG image, Leica scn, MINC image, NIFTI-1 image, PBM image, PGM image, PNG image, PPM image, SPM image, Sakura svslide, TIFF image, TIFF image, TIFF(.tif) image, TIFF(.tif) image, VIDA image, Ventana bif, XBM image, XPM image, Zeiss czi, gz compressed MINC image, gz compressed NIFTI-1 image

input_hierarchy :

Hierarchy, Hierarchy

output_directory :

Directory, Directory

output_csv :

CSV file, CSV file