Sulci recognition with Deep CNN

Description

Process to label a new graph using a 3D U-Net convolutional neural network.

The process can work using a GPU or on CPU. It requires a fair amount of RAM memory (about 4-5 GB). If not enough memory can be allocated, the process will abort with an error (thus will not hang the whole machine).

Paramètres

graph: Graphe de sillons corticaux ( entrée )

input graph to segment

roots: Cortex Catchment Bassins ( entrée )

root file corresponding to the input graph

model_file: Any Type ( entrée )

file (.mdsm) storing neural network parameters

param_file: Any Type ( entrée )

file (.json) storing the hyperparameters (cutting threshold)

skeleton: Cortex Skeleton ( entrée )

skeleton file corresponding to the input graph

grey_white: Grey White Mask ( entrée )

grey white mask corresponding to the input graph

hemi_cortex: CSF+GREY Mask ( entrée )

grey+CSF mask corresponding to the input graph

white_mesh: Maillage de la matière blanche d'un hémisphère ( entrée )

white surface corresponding to the input graph

pial_mesh: Maillage d'un hémisphère ( entrée )

pial surface corresponding to the input graph

allow_multithreading: Booléen ( input )

labelled_graph: Labelled Cortical folds graph ( sortie )

output labelled graph

cuda: Entier ( input )

device on which to run the training(-1 for cpu, i>=0 for the i-th gpu)

fix_random_seed: Booléen ( input )

Use same random sequence

use_capsul_completion: Booléen ( input )

edit_pipeline: Booléen ( input )

capsul_gui: Booléen ( input )

edit_study_config: Booléen ( input )

Informations techniques

Toolbox : Morphologist

Niveau d'utilisateur : 0

Identifiant : sulci_deep_labeling

Nom de fichier : brainvisa/toolboxes/morphologist/processes/Sulci/Recognition/sulci_deep_labeling.py

Supported file formats :

graph :

Graph and data, Graph and data

roots :

gz compressed NIFTI-1 image, Aperio svs, DICOM image, Répertoire, ECAT i image, ECAT v image, FDF image, FreesurferMGH, FreesurferMGZ, GIS image, Hamamatsu ndpi, Hamamatsu vms, Hamamatsu vmu, JPEG image, Leica scn, MINC image, NIFTI-1 image, SPM image, Sakura svslide, TIFF image, TIFF image, TIFF(.tif) image, TIFF(.tif) image, Ventana bif, Zeiss czi, gz compressed MINC image, gz compressed NIFTI-1 image

model_file :

mdsm file, mdsm file

param_file :

JSON file, JSON file

skeleton :

gz compressed NIFTI-1 image, Aperio svs, DICOM image, Répertoire, ECAT i image, ECAT v image, FDF image, FreesurferMGH, FreesurferMGZ, GIS image, Hamamatsu ndpi, Hamamatsu vms, Hamamatsu vmu, JPEG image, Leica scn, MINC image, NIFTI-1 image, SPM image, Sakura svslide, TIFF image, TIFF image, TIFF(.tif) image, TIFF(.tif) image, Ventana bif, Zeiss czi, gz compressed MINC image, gz compressed NIFTI-1 image

grey_white :

gz compressed NIFTI-1 image, Aperio svs, DICOM image, Répertoire, ECAT i image, ECAT v image, FDF image, FreesurferMGH, FreesurferMGZ, GIS image, Hamamatsu ndpi, Hamamatsu vms, Hamamatsu vmu, JPEG image, Leica scn, MINC image, NIFTI-1 image, SPM image, Sakura svslide, TIFF image, TIFF image, TIFF(.tif) image, TIFF(.tif) image, Ventana bif, Zeiss czi, gz compressed MINC image, gz compressed NIFTI-1 image

hemi_cortex :

gz compressed NIFTI-1 image, Aperio svs, DICOM image, Répertoire, ECAT i image, ECAT v image, FDF image, FreesurferMGH, FreesurferMGZ, GIS image, Hamamatsu ndpi, Hamamatsu vms, Hamamatsu vmu, JPEG image, Leica scn, MINC image, NIFTI-1 image, SPM image, Sakura svslide, TIFF image, TIFF image, TIFF(.tif) image, TIFF(.tif) image, Ventana bif, Zeiss czi, gz compressed MINC image, gz compressed NIFTI-1 image

white_mesh :

GIFTI file, GIFTI file, Maillage MESH, MNI OBJ mesh, PLY mesh, Maillage TRI

pial_mesh :

GIFTI file, GIFTI file, Maillage MESH, MNI OBJ mesh, PLY mesh, Maillage TRI

labelled_graph :

Graph and data, Graph and data