Anatomical Structure Partitioning Using Seed-Based Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Determining the boundaries of functional segments within anatomical structures, such as organs, is challenging due to the lack of visible boundaries, which hinders accurate modeling and optimization of medical procedures.
Innovation Solution
A method and system that determine a partitioning of anatomical structure models into segments using a set of seeds derived from labeled tubular structures, allowing for accurate segmentation and output of data representative of these segments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual or conventional methods are used to determine boundaries of functional segments, then the process is simple to implement, but the measurement precision is poor due to lack of visible boundaries
Solution Approach 1:
The patent applies segmentation by dividing the anatomical structure into functional segments based on inferred boundaries. The system segments the anatomical structure into multiple functional segments by determining boundaries that separate regions with different functional characteristics, enabling precise measurement and analysis of each segment without requiring visible boundaries in the original data.
Solution Approach 2:
The patent uses an intermediary approach by introducing a computational model that mediates between the available anatomical data and the required functional segment boundaries. The system uses intermediate representations and inferred boundaries to bridge the gap between conventional imaging data and the need for precise functional segmentation, allowing accurate boundary determination without direct visibility.
2Measurement precision
If automated segmentation algorithms are applied, then the measurement precision improves, but the device complexity increases
Solution Approach 1:
The patent applies parameter changes by adjusting segmentation parameters and thresholds to optimize boundary detection. The system modifies parameters such as boundary strength thresholds, region size constraints, and functional characteristic weights to achieve accurate segmentation while managing computational complexity. By dynamically adjusting these parameters, the system maintains high measurement precision without requiring overly complex algorithms.
3Manufacturing precision
If functional segments are divided into smaller regions, then the manufacturing precision (model accuracy) improves, but the quantity of data to process increases
Solution Approach 1:
The patent segments the anatomical structure into functional segments that balance detail and data management. By dividing the anatomy into meaningful functional regions rather than overly fine-grained segments, the system achieves high model accuracy while controlling the quantity of data that needs to be processed and stored. Each functional segment represents a coherent functional unit that maintains precision without excessive data fragmentation.
Data Source
AI summary
An example method may include determining, by a computing system and based on a set of seeds determined from data representative of a labeled first tubular structure and a labeled second tubular structure in a model of at least a portion of an anatomical structure, a partitioning of the model into segments. The method may further include outputting, by the computing system, data representative of the segments.