Blood Vessel Segmentation Using Local Quality and Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods lack an effective algorithm for the objective extraction and segmentation of deep inferior epigastric artery (DIEA) perforators, which are crucial for breast reconstruction techniques, particularly in the context of DIEP flap procedures, as existing vessel segmentation algorithms are not suitable for this specific application.
Innovation Solution
A method and apparatus for segmenting blood vessels using axial images, involving the reduction of greyscales to binary images, tracking procedures for subcutaneous paths, and minimum cost path methods for intramuscular paths, with the use of local gradient analysis and Frangi vesselness to determine vessel characteristics, enabling accurate extraction of perforator characteristics for surgical planning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If general vessel segmentation algorithms are used, then vessel structures can be visualized, but accurate segmentation of DIEA perforators cannot be achieved
Solution Approach 1:
The patent applies local quality by implementing region-specific processing: the abdomen volume is divided into subcutaneous and intramuscular regions, with different tracking algorithms applied to each. The subcutaneous path uses gradient-based tracking while the intramuscular path uses minimum cost path methods, allowing each region to be processed with the most appropriate technique for its characteristics.
Solution Approach 2:
The patent segments the blood vessel path into two distinct portions: the subcutaneous path from the skin to the fascia layer, and the intramuscular path from the fascia layer to the muscle. This segmentation allows different computational methods to be applied to each portion, improving overall accuracy for DIEA perforator segmentation.
2Extent of automation
If manual marking methods are used, then operator control is maintained, but automation and efficiency are reduced
Solution Approach 1:
The system performs self-service by automatically segmenting the DIEA perforators without requiring manual tracing or marking by operators. The algorithm autonomously identifies the subcutaneous and intramuscular paths through image processing, calculates relevant characteristics, and generates the segmentation, making the system self-sufficient while maintaining accuracy.
Solution Approach 2:
The patent replaces manual mechanical marking operations with automated computational image processing. Instead of operators manually tracing vessels on images, the system uses digital algorithms including gradient analysis, region growing, and minimum cost path calculations to automatically segment and measure the perforators.
3Manufacturing precision
If standard image processing is used, then processing speed is maintained, but segmentation precision for complex vessel paths is insufficient
Solution Approach 1:
The patent applies preliminary action by first defining the fascia layer boundary and identifying entry/exit points before performing the actual path tracking. This preparatory step establishes the anatomical framework and constraints that guide the subsequent subcutaneous and intramuscular path calculations, ensuring precision while avoiding redundant processing.
Solution Approach 2:
The system uses dynamic adaptive algorithms that adjust processing methods based on local image characteristics. The tracking procedure dynamically switches between gradient-based methods in subcutaneous regions and minimum cost path methods in intramuscular regions, optimizing both precision and processing efficiency for each anatomical zone.
Data Source
Figure 1a~3
Figure 2
Figure 4~5
AI summary
A method for segmentation of blood vessels is disclosed. The method comprises acquiring a plurality of images representing axial slices through a region of interest, defining a fascia layer between a muscular region and a subcutaneous region by defining a boundary between high intensity images and low intensity images, and determining a landmark of the blood vessel. A subcutaneous path between the landmark of the blood vessel and the fascia layer and an intramuscular path between the fascia layer and a landmark is calculated.