Search code examples
niftynet

I am struggling to implement multiple channel images

I am trying to train a vnet architecture on a set of 3D MRI volumes and I would like to try adding a channel with a different echo time to each image, effectively making it 4D. I saw that niftynet allows for 4D image input but I received error messages stating that vnet does not allow input that contains a time dimension. What would be the best place for me to make a change to the source code OR how should I combine the channels?

Thanks

Solution

  • NiftyNet follows the nifti1 format where the first three axes are for spatial dimensions, 4th is for time and 5th for multi-modal values. So one way to use multi-channel input is creating .nii files with arrays of [Height, Width, Depth, 1, Channels].