Stereoscopic Volumetric Segmentation With Adaptive 3D Resolution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for segmenting and labeling volumetric data in 3D environments are inefficient, error-prone, and computationally demanding, particularly due to reliance on 2D interfaces and non-stereoscopic views, leading to slow and inaccurate segmentation of large datasets.
Innovation Solution
A system utilizing a hierarchical spatial data structure, such as an octree, to organize and interact with volumetric data in an extended reality environment, allowing direct 3D interaction and labeling through tracked controllers or gaze-based selection, reducing memory load and improving segmentation accuracy by dynamically adjusting resolution based on user interaction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If 2D interfaces and non-stereoscopic views are used for segmentation, then device complexity is reduced, but segmentation precision and productivity deteriorate
Solution Approach 1:
The patent transitions from 2D interface interaction to 3D stereoscopic visualization, allowing users to view and interact with volumetric data in its native three-dimensional space. This dimensional change enables direct spatial reasoning and brush-stroke-based segmentation in 3D, significantly improving segmentation precision without requiring complex multi-device setups
2Manufacturing precision
If high-resolution volumetric data is processed, then segmentation precision is improved, but computational resources and processing time increase
Solution Approach 1:
The patent applies hierarchical data structures (such as octrees) to divide the volumetric dataset into multiple resolution levels. Users can interact with coarse representations for overview and navigation, then progressively refine to higher resolutions only in regions of interest, maintaining high segmentation precision while reducing overall computational load and improving processing efficiency
3Manufacturing precision
If full-resolution volumetric data is displayed, then segmentation precision is improved, but memory load and computational latency increase
Solution Approach 1:
The system dynamically adjusts the resolution of volumetric data based on user interaction and viewing context. High-resolution data is loaded and processed only in the current field of view and regions being actively segmented, while lower-resolution representations are used for background and non-interacted areas, reducing memory bandwidth requirements and computational latency
Data Source
AI summary
Provided is a method for labeling volumetric data, including obtaining, with a computing device, access to volumetric data in a hierarchical spatial data structure, displaying, with the computing device, a multiresolution representation of a three-dimensional image volume in an extended reality environment configured to display volumetric data using the hierarchical spatial data structure, receiving, with the computing device, a selection of a region of interest of the image volume, receiving, with the computing device, user input defining a brush trajectory within the region of interest, determining, with the computing device, which voxels within the image volume that intersect the brush trajectory within the region of interest; and labeling, with the computing device, the identified voxels in memory.