search

ai-med / quickNAT_pytorch

PyTorch Implementation of QuickNAT and Bayesian QuickNAT, a fast brain MRI segmentation framework with segmentation Quality control using structure-wise uncertainty
MIT License
101 stars 36 forks source link

Question about `mri_convert` #25

Open sravan953 opened 4 years ago

sravan953 commented 4 years ago

Hello,

The readme states:

Before deploying our model you need to standardize the MRI scans. Use the following command from FreeSurfer mri_convert --conform The above command standardizes the alignment for QuickNAT, re-samples to isotrophic resolution (256x256x256) with some contrast enhamcement. It takes about one second per volume.

Assuming FreeSurfer is not available, could you please elaborate on the pre-processing steps?

  1. What exactly does it mean to standardize alignment?
  2. Is the contrast enhancement necessary?
han-yeol commented 4 years ago

Obviously, QuickNAT is implemented with Freesurfer. so I think you must use Freesurfer's mri_convert function.

han-yeol commented 4 years ago

Furthermore, This paper is NOT focused on MRI image's preprocessing.