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

Project: White matter tract segmentation in Slicer #1367

Closed
RobinPere opened this issue Jan 20, 2025 · 3 comments · Fixed by #1368
Closed

Project: White matter tract segmentation in Slicer #1367

RobinPere opened this issue Jan 20, 2025 · 3 comments · Fixed by #1368

Comments

@RobinPere
Copy link

Draft Status

Ready - team will start page creating immediately

Category

Segmentation / Classification / Landmarking

Key Investigators

  • Robin Peretzke (German Cancer Research Center, Germany)

Project Description

Diffusion MRI and white matter tract segmentation play a crucial role in many scenarios such as neurosurgery and psychiatry. Although fully automated methods for tract segmentation have been developed, they may fail in specific scenarios, such as cases with significant anatomical deviations caused by tumors, or they lack generalization across diverse species. In these situations, segmentation is typically carried out by human experts. This process is highly time-consuming, challenging to reproduce, and heavily reliant on graphical user interfaces (GUIs) designed for intuitive interaction.

The aim of this project is to enhance the usability of 3D Slicer for white matter tract segmentation and interaction. Improvements will focus on creating more intuitive tools for user interaction and integrating novel algorithms into the software to streamline the segmentation process.

Objective

Objective A
Familiarizing with the existing SlicerDMRI infrastructure is essential, including understanding its current capabilities and workflows. This process involves building a new module while ensuring packages and libraries are updated to maintain compatibility and performance.

Objective B
Exploring and implementing simple white matter tract dissection interactions, such as boolean operations with fibers and regions of interest (ROIs), to improve interactivity and usability within the platform.

Objective C
Investigating and incorporating additional (semi-)automatic tract segmentation algorithms into SlicerDMRI to extend its functionality and better support complex use cases (such as atTRACTive¹)

Approach and Plan

  1. The first step involves exploring the SlicerDMRI architecture, existing documentation, and module-building workflows. Efforts will focus on understanding the integration of relevant libraries and updating packages as needed. This step is fundamental for further developing.

  2. Work will focus on enabling basic operations, such as boolean interactions between fibers and ROIs.

  3. The aim is to explore and implement additional tract segmentation algorithms that align with the SlicerDMRI framework.

Progress and Next Steps

  1. Describe specific steps you have actually done.

Illustrations

No response

Background and References

[1] Peretzke, Robin, et al. "atTRACTive: semi-automatic white matter tract segmentation using active learning." International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer Nature Switzerland, 2023.

@pieper
Copy link
Contributor

pieper commented Jan 20, 2025

@RobinPere I'll be interested in discussing this with you and helping you understand SlicerDMRI.

Do you have a preprint of the paper you could link to from the project page?

Copy link

github-actions bot commented Jan 20, 2025

Project Page Pull Request Creation

COMPLETED: See #1368

@RobinPere
Copy link
Author

@RobinPere I'll be interested in discussing this with you and helping you understand SlicerDMRI.

Do you have a preprint of the paper you could link to from the project page?

@pieper That would be awesome. Thanks,Steve!
Here’s the arxiv link of the active learning for tractography tract segmentation paper arXiv link.

Additionally, you might find our software, MitkDiffusion. Maybe here we can find some inspiration...

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
3 participants