search

DeepRegNet / DeepReg

Medical image registration using deep learning
Apache License 2.0
569 stars 79 forks source link

Train with nifti #753

Closed AmericaBG closed 3 years ago

AmericaBG commented 3 years ago

Hi! First of all, thank you very much for sharing your code. it's a great job, congratulations!

I would like to train my own model with MR Images in .nii format. The shape is 256x256xN slices. Is it posible with your code? Could you give me some advice about how I can do it or/and what I need to modify?

Thank you very much in advance!

YipengHu commented 3 years ago

Hi! First of all, thank you very much for sharing your code. it's a great job, congratulations!

I would like to train my own model with MR Images in .nii format. The shape is 256x256xN slices. Is it posible with your code? Could you give me some advice about how I can do it or/and what I need to modify?

Thank you very much in advance!

Is it a case that you have variable number of slices in z direction? yes, most current algorithms require the same input size, you can either a) pre-process your images by re-sampling/cropping - i guess this would be application-specific; or b) configure a fixed image_shape so it uses a built-in re-sampling function to pre-re-sample all iamges to the same shape (https://deepreg.readthedocs.io/en/latest/docs/configuration.html#unpaired). does it answer your question?

stale[bot] commented 3 years ago

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.