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

[3.10-BT] 3D Brush Tool with Connected Region Filling and Adaptive Thresholding #4509

Open
sedghi opened this issue Nov 14, 2024 · 0 comments

Comments

@sedghi
Copy link
Member

sedghi commented Nov 14, 2024

Purpose

This feature introduces a 3D brush tool for precise voxel-level segmentation, enabling selective region filling based on grayscale similarity and spatial connectivity. This tool enhances segmentation accuracy by allowing users to fill connected, similar regions in 3D space, with adjustable parameters and interactive previews to support dynamic, detailed editing.

Why This Matters

In medical imaging and other volumetric data applications, accurate segmentation is critical. Traditional 2D tools can be limiting when working with 3D data, as they don’t account for connectivity across slices or allow for efficient segmentation of homogeneous regions. The 3D brush tool addresses these limitations by letting users segment directly in 3D, guided by grayscale similarity and spatial connectivity. This makes it easier to capture complex structures with precision, reducing manual editing time and improving segmentation quality.

Key Changes

  • 3D Voxel-Level Segmentation: The tool operates on a spherical volume, enabling users to define connected regions in 3D based on grayscale similarity to the central voxel, resulting in more accurate segmentation within homogeneous areas.
  • Voxel Selection by Grayscale Similarity: Fills only connected voxels that share similar grayscale values with the central brush area, ensuring selective and targeted segmentation.
  • Interactive Preview: A semi-transparent overlay appears on targeted voxels when the brush hovers over them, allowing users to visualize the potential fill area before committing to the action.
  • Adjustable Parameters: Users can fine-tune the Grayscale Range to control similarity sensitivity and adjust the Brush Diameter to control the size of the segmentation area.
  • Eraser Functionality: Users can remove overlapping voxels by starting the brush outside segmented regions, providing a simple way to refine and clean up segmented areas.

Impact on Users and Developers

  • For Users: The 3D brush tool provides a powerful, intuitive way to perform precise voxel-level segmentation directly in 3D space. Users will be able to segment regions based on grayscale similarity, with interactive previews that let them visualize and adjust their selections before applying changes. This significantly enhances the control and flexibility in complex segmentation tasks, reducing the time and effort required to achieve high-quality results.
  • For Developers: The tool integrates seamlessly with existing segmentation workflows, offering developers an advanced option to support 3D segmentation requirements. Adjustable parameters like grayscale range and brush diameter give developers flexibility to customize the tool’s behavior to match different application needs, ensuring that it can be tailored to specific imaging contexts.

This 3D brush tool is a significant addition to the segmentation toolkit, offering users greater accuracy and ease of use for complex voxel-level editing tasks across 3D datasets.

@sedghi sedghi changed the title [Feature Request] 3D Brush Tool with Connected Region Filling and Adaptive Thresholding [3.10-BT] 3D Brush Tool with Connected Region Filling and Adaptive Thresholding Nov 14, 2024
@sedghi sedghi mentioned this issue Nov 14, 2024
10 tasks
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant