Dženan Zukić

You should be able to use `.nii.gz` files directly.

Could/should `WriteParameterFile` and related methods be used for this?

```py import itk import numpy as np fixed_image = itk.imread("target_image.mha") moving_image = itk.imread("source_image.mha") registered, parameters = itk.elastix_registration_method(fixed_image, moving_image, log_to_console=True) ``` crashes silently for me: ```log Elastix initialization of all components...

How about `parameter_map['RandomSeed'] = ['30101983']`? In the parameter file that might be `(RandomSeed 30101983)`.

You should be able too look up all the Elastix parameters [here](https://elastix.lumc.nl/doxygen/parameter.html), but the page is not working for me right now. @N-Dekker @ViktorvdValk Is that just me, or is...

The only thing which comes to mind would be image lingering in memory, causing disk swapping during registration. But 400 slices probably can't do that due to small size. So...

Deformable transforms are not necessarily invertible. I am unaware of a convenient function to invert them. @N-Dekker or @mstaring might know of a way which is not too inconvenient?

What version of Python are you using? There are no prebuilt packages for 3.12.

If this is expected behavior, perhaps documentation could be improved. What is the difference between `SetExternalInitialTransform` and `SetInitialTransform`?

`read_slicer_fiducials` is from here: https://github.com/KitwareMedical/HASI/blob/d58acf4cda836bdedd1b7531dddc8ca7b20b396a/src/hasi/mouse_femur_tibia_ct_morphometry.py#L39-L67 Here is how I construct initial transform: ```py def register_landmarks(fixed_landmarks, moving_landmarks): transform_type = itk.Transform[itk.D, 3, 3] landmark_transformer = itk.LandmarkBasedTransformInitializer[transform_type].New() rigid_transform = itk.Similarity3DTransform[itk.D].New() landmark_transformer.SetFixedLandmarks(fixed_landmarks) landmark_transformer.SetMovingLandmarks(moving_landmarks) landmark_transformer.SetTransform(rigid_transform)...