search

josedolz / LiviaNET

This repository contains the code of LiviaNET, a 3D fully convolutional neural network that was employed in our work: "3D fully convolutional networks for subcortical segmentation in MRI: A large-scale study"
MIT License
161 stars 52 forks source link

how did you got the GT? #27

Closed maximedieudonne closed 4 years ago

maximedieudonne commented 4 years ago

Hi Jose, The GT are available only on .mat without header, Could you please give me some information about the GT ? how did you made them for exemple ?

Best regards,

Maxime dieudonné

josedolz commented 4 years ago

Hi @MaximeDdnn

This is explained in the paper. For IBSR, images are provided with their corresponding GT. For the ABIDE dataset, we employed FreeSurfer to generate the masks.

Jose

maximedieudonne commented 4 years ago

thank you for your quick answer! :) the five images MR_Imgx with thier corresponding Label and GT are from IBSR ? I thougth it was from ABIDE and you make the GT manualy

josedolz commented 4 years ago

No, the few subjects shared (as .mat files) are from ABIDE and the corresponding GTs are obtained with Freesurfer. We didn't perform manual segmentations on any MRI image.

maximedieudonne commented 4 years ago

thank you for the information