Skip to content

Instantly share code, notes, and snippets.

@jcreinhold

jcreinhold/example_tiramisu_brulee_predict.csv

Last active July 22, 2021 19:53
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save jcreinhold/8787667df85839be66355089eb148c43 to your computer and use it in GitHub Desktop.
Save jcreinhold/8787667df85839be66355089eb148c43 to your computer and use it in GitHub Desktop.
Download ZIP
Example CSV for lesion-predict CLI in tiramisu-brulee
Raw
example_tiramisu_brulee_predict.csv
subject flair pd t1 out
pred_subject_1 /path/to/flair_1.nii.gz /path/to/pd_1.nii.gz /path/to/t1_1.nii.gz /path/to/save/predicted_segmentation_1.nii.gz
pred_subject_2 /path/to/flair_2.nii.gz /path/to/pd_2.nii.gz /path/to/t1_2.nii.gz /path/to/save/predicted_segmentation_2.nii.gz
@jcreinhold
Copy link
Author

The names in the subject column are arbitrary designators the row and do not affect data loading.

The non-label columns in the example training CSV file are the same ones used here.

The out column holds the paths to save each predicted segmentation image volume.

The order of the columns doesn't matter. The non-label/non-out columns are sorted for input to the network. For example, in this case, the first channel will be a FLAIR image, the second channel will be a PD-w image, and the third channel will be a T1-w image (if you are using a 3D network).

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment