The result is the same with and without pointset about itkelastix HOT 6 CLOSED

I believe you have to specify registration parameters that include point based metrics.

Developer docs on the metric: https://elastix.lumc.nl/doxygen/classelastix_1_1CorrespondingPointsEuclideanDistanceMetric.html

This link has some info and code from simpleelastix which is, N.B., not fully transferable but the principle is the same: https://simpleelastix.readthedocs.io/PointBasedRegistration.html

A good strategy may be to make to make two rigid parameter maps, the first with the corresponding points distance metric, and the second without. This workflow assumes your first rigid will use the corresponding points, find a good registration, then proceed with fully automatic approaches.

Heath

I added the following line and the problem was solved! Thank you very much for your help.

        parameter_map_rigid['Metric'] = [original_metric[0],
                                         'CorrespondingPointsEuclideanDistanceMetric']

from itkelastix.

If fixed and moving images are provided, maybe the point sets are ignored? Somebody who knows elastix better could answer this authoritatively. You can also test it by removing fixed_image, moving_image, parameters.

from itkelastix.

If fixed and moving images are provided, maybe the point sets are ignored? Somebody who knows elastix better could answer this authoritatively. You can also test it by removing fixed_image, moving_image, parameters.

Thank you for your quick reply. But in examples 5 and 9, the images and point sets are given together. I get this error when I remove fixed_image and moving_image:
ITK ERROR: ElastixRegistrationMethod(0x654ae30): Input FixedImage is required but not set.

I get this error when I only add fixed_image:
TypeError: Expecting argument of type itkImageF2 or itkImageSourceIF2.

from itkelastix.

I believe you have to specify registration parameters that include point based metrics.

Developer docs on the metric:
https://elastix.lumc.nl/doxygen/classelastix_1_1CorrespondingPointsEuclideanDistanceMetric.html

This link has some info and code from simpleelastix which is, N.B., not fully transferable but the principle is the same:
https://simpleelastix.readthedocs.io/PointBasedRegistration.html

A good strategy may be to make to make two rigid parameter maps, the first with the corresponding points distance metric, and the second without. This workflow assumes your first rigid will use the corresponding points, find a good registration, then proceed with fully automatic approaches.

Heath

from itkelastix.

Indeed, example 5 shows how to create a parameter map with the correct metrics in this case.
Keep in mind that example 5 shows how to use a point set to help the registration of images, and example 9 shows how to transform the point sets.

from itkelastix.

Indeed, example 5 shows how to create a parameter map with the correct metrics in this case. Keep in mind that example 5 shows how to use a point set to help the registration of images, and example 9 shows how to transform the point sets.

You were absolutely right. I didn't notice this difference.

from itkelastix.