8000 How can I get the trackings from the bundle masks that are predicted from my model? · Issue #81 · MIC-DKFZ/TractSeg · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

How can I get the trackings from the bundle masks that are predicted from my model? #81

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 cl 8000 icking “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
Closed
luqily opened this issue Nov 24, 2019 · 4 comments
Closed

How can I get the trackings from the bundle masks that are predicted from my model? #81

luqily opened this issue Nov 24, 2019 · 4 comments

Comments

@luqily
Copy link
luqily commented Nov 24, 2019

Hi, I am sorry to bother you again.
I have gotten the bundle masks from my own model. And how can I get the trackings from them?
@wasserth
Copy link
Collaborator

Just look into the documentation. There is a detailed description. It's not difficult: https://github.com/MIC-DKFZ/TractSeg#create-bundle-specific-tractograms

@luqily
Copy link
Author
luqily commented Nov 25, 2019

Just look into the documentation. There is a detailed description. It's not difficult: https://github.com/MIC-DKFZ/TractSeg#create-bundle-specific-tractograms

Thanks for your reply.
But I only have trained the model for tract_segmentation. I don't have endings_segmentation and TOM. Can I use this to get the trackings?

@wasserth
Copy link
Collaborator

If you want to run with your own training data, you have to retrain your model for those as well. This is a bit more complicated because you first have to preprocess the training streamlines to get endings masks and peak maps for training.
For endings segmentations see this code: tractseg/tractseg/libs/create_endpoints_mask_with_clustering.py.
For peaks maps see this issue: #82

@luqily
Copy link
Author
luqily commented Nov 25, 2019

If you want to run with your own training data, you have to retrain your model for those as well. This is a bit more complicated because you first have to preprocess the training streamlines to get endings masks and peak maps for training.
For endings segmentations see this code: tractseg/tractseg/libs/create_endpoints_mask_with_clustering.py.
For peaks maps see this issue: #82

Thanks so much!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@wasserth @luqily
0