3D Annotation Tool With Slice Interpolation For Segmentation Editing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current 3D segmentation tools are inadequate for editing existing segmentations, often resulting in inaccurate delineation of areas of interest in 2D images from 3D scans, leading to time-consuming manual editing and potential degradation of segmentation quality, especially in complex shapes.
Innovation Solution
A system with a user interface for manual editing and a 3D interpolation component that applies selective localized interpolation to update segmentations, maintaining initial contours where necessary and modifying only areas corresponding to manual edits, based on distance or connectivity criteria.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual editing is applied to correct initial segmentation inaccuracies, then segmentation accuracy is improved, but time consumption increases
Solution Approach 1:
The patent divides the segmentation correction process into two distinct phases: initial automated segmentation and subsequent manual editing only where needed. This segmentation of the workflow allows the system to leverage automated methods for most of the volume while applying manual precision only to problematic regions, thereby reducing overall time consumption while maintaining high accuracy.
Solution Approach 2:
Instead of requiring manual editing of the entire segmented volume, the patent applies manual editing partially—only to regions where the initial automated segmentation is inaccurate or ambiguous. This partial action approach significantly reduces time consumption while still achieving the necessary segmentation accuracy for the whole volume.
2Ease of operation
If existing 3D segmentation tools are used for editing, then editing capability is provided, but segmentation quality degrades due to poor suitability for editing tasks
Solution Approach 1:
The patent segments the editing operation into localized modifications within a defined editing region, rather than applying global editing operations. This allows the system to maintain high segmentation quality by focusing editing efforts only where needed and using interpolation to preserve accuracy in non-edited regions.
Solution Approach 2:
The patent applies local quality by performing interpolation and editing operations locally within a defined editing region rather than globally across the entire volume. This ensures that segmentation quality is maintained in regions not subject to manual editing while allowing flexible editing where needed.
3Measurement precision
If manual editing is performed on 2D slices, then local correction accuracy is improved, but propagation of edits to other slices becomes problematic
Solution Approach 1:
The patent performs preliminary actions by defining an editing region and establishing interpolation parameters before executing the manual edit. This preliminary setup ensures that when edits are propagated to other slices through interpolation, the propagation is reliable and consistent with the local anatomy, maintaining both local correction accuracy and overall reliability.
Solution Approach 2:
The patent introduces interpolation as an intermediary mechanism that bridges the gap between local manual edits on 2D slices and the corresponding regions in other slices. This intermediary process ensures that edits propagate reliably while maintaining anatomical consistency, solving the problem of unreliable edit propagation.
4Device complexity
If global interpolation is applied to propagate edits, then edit propagation is simplified, but local anatomical accuracy is lost in non-edited regions
Solution Approach 1:
The patent segments the volume into an editing region and non-editing regions, applying different processing strategies to each. Global interpolation is applied only within the localized editing region, while non-edited regions maintain their original segmentation. This segmentation approach preserves local anatomical accuracy in non-edited regions while still providing simplified propagation within the edited region.
Solution Approach 2:
The patent applies local quality by restricting interpolation operations to a defined editing region rather than applying global interpolation across the entire volume. This ensures that local anatomical accuracy is preserved in non-edited regions while still achieving efficient edit propagation within the relevant local area.
Data Source
AI summary
A 3D segmentation editing system accurately updates the segmentations of non-edited images of a 3D scan to reflect segmentation edits applied to other images of the scan using localized interpolation. In one or more embodiments, rather than replacing the entireties of the initial segmentations of non-edited images with newly generated, globally interpolated segmentations, the segmentation editing system applies a distance-based criterion to the interpolation of segmentation edits, such that only portions of the segmentations of the non-edited images that correspond to areas that were manually annotated in the edited images will be modified by the interpolation process, and the initial segmentations will be maintained outside of those edited areas. In this way, the system merges the interpolated segmentation with the initial segmentation for each non-edited image in a manner that mitigates unreliable modifications to the initial segmentations in areas far from the edited areas.