search

MIC-DKFZ / nnUNet

Apache License 2.0
5.71k stars 1.73k forks source link

Issue with nnunetpreprocess #373

Closed krishna1996 closed 3 years ago

krishna1996 commented 3 years ago

According to the website, the folder structure has to be as shown in the first image. But as per the downloaded data, the modalities are not mentioned as shown in the second image.

How can I get 'BRATS_001.nii.gz' from BRATS_001_0000.nii.gz , BRATS_001_0001.nii.gz , BRATS_001_0002.nii.gz , BRATS_001_0003.nii.gz

6AE21A94-4F9C-4744-B106-0D2E469FA9CF

3A2E937A-6DE7-4EBF-818C-0E4BA7083857

Kindly help.

FabianIsensee commented 3 years ago

Hi, I am really busy at the moment and it would help a great deal if you could have a look at the documentation first. You need to follow the instructions here: https://github.com/MIC-DKFZ/nnUNet/blob/master/documentation/dataset_conversion.md

This page is referenced in the main readme (https://github.com/MIC-DKFZ/nnUNet#dataset-conversion) so it should not be hard to miss. Best, Fabian

krishna1996 commented 3 years ago

Yes, I have gone through the code ,could you point where in this code you have related the images of different modalities to a single label here. Thank you.

FabianIsensee commented 3 years ago

You are confusing two very different datasets. The dataset you have opened is the Task01_BrainTumour from the MSD. The file you link to is the BraTS 2018 data. For the Task01 dataset, please follow the instructions from my previous response

FabianIsensee commented 3 years ago

have you been able to solve this?