Which file to use exactly for the evaluation of MRI dataset?

[ridhimagarg]

Which file to use exactly for the evaluation of MRI dataset?

[Julian-Wyatt]

Ah yes - wonderful question because that really was confusing.

So I went through all of those .nii files and used the COR_3D_IR images, which I believe are the T1 weighted images from that dataset.

Does this help?

[Julian-Wyatt]

Hi, my specific pipeline, converted the .nii files to .npy files as they are much quicker to read into PyTorch. The function I used to automate this is main() in dataset.py.

These resultant .npy files are those placed in that 'raw' folder. You can however structure your folders however you see fit.

Please let me know if this helps.

[ridhimagarg]

Thanks for your response!!

Yes, but I was thinking if which images you are utilising in your original paper for evaluating as for each scan there are multiple folders which contain .nii files. Like for this scan -:

Which folder should I use?

[ridhimagarg]

Thanks a lot!!