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.

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

Improve NODDI step in the pipeline #14

Open
ebrahimebrahim opened this issue Mar 6, 2024 · 1 comment · May be fixed by #20
Open

Improve NODDI step in the pipeline #14

ebrahimebrahim opened this issue Mar 6, 2024 · 1 comment · May be fixed by #20
Assignees

Comments

@ebrahimebrahim
Copy link
Member

  • The current NODDI step using dmipy is too slow
  • It should be possible to choose between Watson and Bingham NODDI

The NODDI step in the pipeline is currently using the dmipy implementation, but it's super slow and can take hours to handle just one image. We should try something else. There's MDT, which has gpu accelerated NODDI estimation, and also AMICO. We should look into both of these.

@ebrahimebrahim
Copy link
Member Author

I just saw to a DIPY workshop talk by Gary Zhang where he recommended using either AMICO or some type of machine learning to quickly get close to the true value, and then from there to use conventional fitting to refine the result.

@ebrahimebrahim ebrahimebrahim self-assigned this Apr 2, 2024
@ebrahimebrahim ebrahimebrahim linked a pull request Apr 2, 2024 that will close this issue
@ebrahimebrahim ebrahimebrahim linked a pull request Apr 2, 2024 that will close this issue
@ebrahimebrahim ebrahimebrahim moved this to Will go to Q2 in ABCD Y2Q1 Aug 12, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
Status: Will go to Q2
Development

Successfully merging a pull request may close this issue.

2 participants