3D Medical Contouring via Non-Parallel Slice Edge Integration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for delineating anatomic structures in medical image data are time-consuming and require significant manual intervention, especially when the structure's shape does not fit a pre-defined library of contours.
Innovation Solution
The system calculates a three-dimensional shell representing the anatomic structure by using edges from non-parallel image slices with different orientations, allowing for high-quality delineation with minimal manual intervention and without relying on contour libraries, using a processing unit to generate and iteratively improve a triangular mesh structure that approximates the structure's surface.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If manual contouring is performed in two-dimensional slices using simple drawing tools, then the delineation process is straightforward and requires minimal specialized tools, but it takes several hours to delineate all structures of interest in a three-dimensional data set
Solution Approach 1:
The patent segments the 3D contouring task into multiple 2D slice contouring operations. By processing each axial slice independently and then assembling the results into a 3D representation, the system enables users to use simple 2D drawing tools while reducing overall processing time through parallelizable slice-by-slice operations.
Solution Approach 2:
The patent transforms the contouring process from a purely 3D operation to a series of 2D operations on axial slices. This dimensional reduction allows users to work with simpler 2D drawing interfaces while the system reconstructs the 3D structure, effectively trading computational complexity for user operational simplicity.
2Productivity
If automated model-based organ delineation is used, then the delineation process becomes faster and more consistent, but the system fails when the anatomic structure's shape does not fit the pre-defined library of contours
Solution Approach 1:
The patent employs dynamic deformation models that can adapt their shape parameters during the fitting process. Instead of using fixed pre-defined contours, the system allows the model to dynamically adjust its geometry to match the actual anatomic structure, enabling it to handle complex and irregular shapes while maintaining automated processing speed.
Solution Approach 2:
The system changes the parameters of the deformation model based on the specific anatomic structure being delineated. By adjusting shape parameters adaptively rather than using fixed library contours, the system can accommodate a wide variety of anatomical variations and complex geometries while maintaining consistent automated processing.
3Manufacturing precision
If interactive tools are used to correct problematic areas in automated model adaptation, then the delineation accuracy is improved, but the overall process becomes more time-consuming
Solution Approach 1:
The patent implements an iterative feedback mechanism where the system automatically evaluates the quality of the delineated structures and provides feedback on problematic areas. This enables the system to identify and prioritize correction needs, allowing users to focus interactive correction only on problematic regions rather than reviewing the entire 3D structure, thereby reducing total correction time while maintaining high 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, which has a first orientation in the source data. 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, which has a second orientation in the source data. 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.