You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
In our effort to make ClinicaDL more open to other disease than Alzheimer, it would be great to remove the diagnosis option from train, predict and interpret command.
Indeed the diagnosis filtering should be done upstream when defining the different TSV files (list of subject/sessions) so it is more clear to see what a group corresponds too.
So for instance if someone would like to create a test set with only diagnosis A, then he should create the corresponding TSV (with the corresponding TSV tool) with only subject diagnosed with A and then create a group with this TSV.
That would allow us to remove the hard coded diagnose from the command line and thus simplify it a bit.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
In our effort to make ClinicaDL more open to other disease than Alzheimer, it would be great to remove the diagnosis option from train, predict and interpret command.
Indeed the diagnosis filtering should be done upstream when defining the different TSV files (list of subject/sessions) so it is more clear to see what a group corresponds too.
So for instance if someone would like to create a test set with only diagnosis A, then he should create the corresponding TSV (with the corresponding TSV tool) with only subject diagnosed with A and then create a group with this TSV.
That would allow us to remove the hard coded diagnose from the command line and thus simplify it a bit.
Beta Was this translation helpful? Give feedback.
All reactions