3D Shell Interpolation for Medical Image Contouring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for organ delineation in radiotherapy planning are time-consuming and require significant manual intervention, especially when dealing with anatomical structures whose shapes do not fit predefined contour libraries.
Innovation Solution
A system and method that use a processing unit to calculate a three-dimensional shell representing an anatomical structure by interpolating between edges identified in multiple two-dimensional image slices, allowing for high-quality delineation with minimal manual input and without relying on contour libraries, using algorithms like shape-based interpolation and triangular mesh structures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If manual contouring in two-dimensional slices is used, then the delineation can be performed for any anatomical structure, but the process is time-consuming and tedious
Solution Approach 1:
The patent transitions from two-dimensional slice-by-slice contouring to three-dimensional surface rendering. By creating a 3D shell representation of the anatomical structure, the system allows contouring in three dimensions, significantly reducing the time required while maintaining applicability to any anatomical structure regardless of shape complexity.
Solution Approach 2:
The patent introduces an intermediate 3D shell model that serves as a mediator between the 2D image data and the final contouring result. This shell model can be deformed and adapted to match anatomical structures, providing an efficient intermediate representation that speeds up the delineation process while maintaining versatility.
2Productivity
If automated model-based delineation is used, then the process is faster, but it fails for structures that do not fit predefined contour libraries
Solution Approach 1:
The patent employs dynamic, deformable 3D shell models that can adapt their shape to match various anatomical structures. Unlike static predefined contours, these models can be deformed interactively to accommodate any anatomical shape, combining the speed of automation with the flexibility to handle varied structures.
Solution Approach 2:
The system changes the parameters of the 3D shell model (such as surface geometry, volume, and shape characteristics) to match the target anatomical structure. By adjusting these parameters dynamically, the system can delineate structures of any shape while maintaining fast automated processing.
3Measurement precision
If interactive tools are used to correct automated delineation, then accuracy is improved, but the complexity of the system increases
Solution Approach 1:
The system provides self-service capabilities where the 3D shell model automatically adapts to the anatomical structure based on image data, requiring minimal manual intervention. The interactive tools are simplified because they work with the already-processed 3D model rather than raw 2D slices, reducing system complexity while maintaining accuracy.
Data Source
AI summary
An anatomic structure of interest is contoured in 3D source data by selecting a first subset of data in a first image slice at a first axial position (z1). A first set of instructions identifies a first edge (E1) of the anatomic structure of interest in the first image slice. Then, a second subset of data is selected in a second image slice at a second axial position (z2); and a second set of instructions identifies a second edge (E2) of the anatomic structure of interest in the second image slice. A three-dimensional shell (3DS) is calculated based on the first and second edges (E1; E2) and the source data (SD). The three-dimensional shell (3DS) represents an approximation of a delimiting surface that separates the anatomic structure of interest from adjoining tissues in the 3D source data.