Adaptive Mesh Contouring via Multi-Image Feature Registration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current image segmentation methods face challenges in accurately establishing the contour of structures, especially when information is missing or unreliable in one image, as they rely solely on feature information from a single modality or image.
Innovation Solution
A system that initializes an adaptive mesh using feature information from multiple images, deforms it based on both images, and establishes forces acting on the mesh to enhance accuracy, incorporating a transform-establishing subsystem for coordinate registration and a general outline-providing subsystem to prevent false boundaries, allowing for the combination of feature information from different imaging modalities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If image segmentation relies solely on feature information from a single image, then the processing is simple and fast, but the accuracy and reliability of contour establishment deteriorates when information is missing or unreliable
Solution Approach 1:
The patent combines feature information from multiple images (first image and second image) to establish the contour of a structure. The adaptive mesh is deformed based on feature information from both images, allowing complementary information to improve contour accuracy when one image has missing or unreliable data.
Solution Approach 2:
The patent introduces an adaptive mesh as an intermediary object that is initialized and then deformed based on feature information from multiple images. This mesh serves as a mediator that integrates information from different images to establish the final contour, resolving the contradiction between using multiple data sources and maintaining system simplicity.
2Reliability
If feature information from multiple images is used to deform the adaptive mesh, then the reliability and accuracy of contour establishment improves, but the processing complexity and computational requirements increase
Solution Approach 1:
The patent employs a dynamic adaptive mesh that can be deformed based on feature information from multiple images. The mesh transitions from an initialized state to a deformed state that reflects the integrated information, allowing the system to adapt dynamically to the available data while maintaining reliability.
Solution Approach 2:
The patent changes the parameters of the adaptive mesh (position, shape, contour) based on feature information from multiple images. By adjusting mesh parameters in response to complementary information from different images, the system improves reliability without requiring a fundamentally different approach.
3Measurement precision
If the adaptive mesh is deformed based on feature information from multiple images, then missing or unreliable information in one image can be compensated, but the time and computational resources required increase
Solution Approach 1:
The patent performs preliminary initialization of the adaptive mesh before deforming it based on feature information from multiple images. This preliminary setup allows the system to efficiently integrate information from multiple sources during the deformation phase, reducing overall processing time while maintaining high segmentation accuracy.
Data Source
AI summary
A system for establishing a contour of a structure is disclosed. An initialization subsystem (1) is used for initializing an adaptive mesh representing an approximate contour of the structure, the structure being represented at least partly by a first image, and the structure being represented at least partly by a second image. A deforming subsystem (2) is used for deforming the adaptive mesh, based on feature information of the first image and feature information of the second image. The deforming subsystem comprises a force-establishing subsystem (3) for establishing a force acting on at least part of the adaptive mesh, in dependence on the feature information of the first image and the feature information of the second image. A transform-establishing subsystem (4) is used for establishing a coordinate transform reflecting a registration mismatch between the first image, the second image, and the adaptive mesh.