search

ANTsX / ANTsPyNet

Pre-trained models and utilities for deep learning on medical images in Python
https://antspynet.readthedocs.io
Apache License 2.0
200 stars 28 forks source link

Understanding the DKT Parcellation for skull stripped data #54

Closed Jeffotter closed 2 years ago

Jeffotter commented 2 years ago

Hi, I am very new to all this and might have somewhat of a novice question. I am attempting to DKT parcellate a brain from a well-known ANDI Dataset in python. I understand that the preprocessing for the Desekan_Killany_Tourville function uses "croppedMni152" to aid in registration during its preprocessing. Is it wrong for me to utilize this preprocessing on an already skull-stripped data set? Or does the Ants account for this? Thank you in advance!

ntustison commented 2 years ago

It is preferred if the input is the raw T1 image. However, you can try to do the preprocessing yourself. Just make sure you set do_preprocessing=False.

Jeffotter commented 2 years ago

Thank you Nick, I'll check around to see what I can get, best results so far is using the model as is