Organ and Tumor Segmentation via Evolution Equations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Segmentation of primary and metastatic tumors, as well as heterogeneous organs like the liver, spleen, and kidney in cross-sectional images is challenging due to their complex structures, requiring accurate and efficient delineation and volume measurement for effective therapy response assessment and non-invasive diagnosis.
Innovation Solution
A method involving the determination of initial boundary positions using image data, with the evaluation of evolution equations that consider topographical distances and statistical metrics to refine and accurately segment organs and tumors, employing active contour models and topographical effects to handle complex boundaries and heterogeneous properties.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional segmentation methods are used on heterogeneous organs and tumors, then the segmentation process is simpler, but the segmentation accuracy deteriorates due to complex structures and heterogeneous properties
Solution Approach 1:
The patent applies segmentation by dividing the image processing into distinct stages: initial boundary detection, evolution equation evaluation, and boundary refinement. Multiple boundaries are processed separately and then integrated, allowing complex heterogeneous structures to be handled through systematic division of the segmentation task into manageable components.
Solution Approach 2:
The patent employs dynamic evolution equations that allow boundaries to adapt and evolve iteratively based on image data and topographical distances. The boundaries are not static but dynamically adjusted through multiple evaluations of evolution equations, enabling the segmentation to adapt to heterogeneous properties within organs and tumors.
2Measurement precision
If accurate delineation of complex anatomical structures is pursued, then diagnosis quality improves, but processing time increases
Solution Approach 1:
The patent performs preliminary boundary detection and initial positioning before final refinement. Evolution equations are evaluated in advance with initial boundary data, and topographical distances are pre-calculated, allowing the final segmentation to be achieved more efficiently without sacrificing accuracy.
Solution Approach 2:
The patent maintains continuous refinement of boundaries through iterative evaluation of evolution equations. Rather than discrete, repeated processing steps, the method continuously adjusts boundaries based on accumulating information from image data and topographical analysis, improving efficiency while maintaining high delineation accuracy.
Data Source
AI summary
Techniques for segmentation of organs and tumors and cells in image data include revising a position of a boundary by evaluating an evolution equation that includes differences of amplitude values for voxels on the boundary from a statistical metric of amplitude of voxels inside, and from a statistical metric of amplitude of voxels outside, for a limited region that lies within a distance r of the boundary. The distance r is small compared to a perimeter of the first boundary. Some techniques include determining a revised position of multiple boundaries by evaluating an evolution equation that includes differences in a first topographical distance from a first marker and a second topographical distance from a second marker for each voxel on the boundary, and also includes at least one other term related to boundary detection.