Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Registration benchmarking - image loss #2565

Closed
kate-sann5100 opened this issue Jul 9, 2021 · 2 comments
Closed

Registration benchmarking - image loss #2565

kate-sann5100 opened this issue Jul 9, 2021 · 2 comments
Labels
Feature request
Milestone
Image Registration

Comments

@kate-sann5100
Copy link
Collaborator

Is your feature request related to a problem? Please describe.
MONAI currently have implemented 2 image similarity loss for registration application:

  • LocalNormalisedCrossCorrelationLoss
  • GlobalMutualInformationLoss

Both loss has been tested numerically (comparing with DeepReg) in the unity tests. However, it would be great to include the following tests:

  • More tests on numerical accuracies by comparing it with more well established implementations
  • Speed comparison

This issue is built for the detailed discussions on designing the tests. All kinds of thoughts and advices are welcomed.

Describe the solution you'd like

Describe alternatives you've considered

Additional context
@kate-sann5100
Copy link
Collaborator Author

@YipengHu

@YipengHu
Copy link

this may be used as reference: https://github.com/ANTsX/ANTsPy/blob/master/ants/utils/image_similarity.py

@wyli wyli added this to the Image Registration milestone Jul 26, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
Feature request
Projects
MONAI core backlog
Status: No status
Milestone
Image Registration
Development

No branches or pull requests
4 participants
@wyli @YipengHu @Nic-Ma @kate-sann5100