Vessel Geometry Extraction Using Poker Chip Representation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional medical imaging techniques face challenges in accurately and efficiently extracting geometry from images of tubular body structures, such as blood vessels, due to difficulties in understanding 3D structures from 2D slices and limitations in quantitative geometry analysis, leading to incomplete and unsatisfactory results in diagnostic and research applications.
Innovation Solution
The development of methods and apparatus for extracting geometry from medical images using a 'Poker Chip' representation, where vessels are modeled as linked circular or elliptical disks, allowing for the determination of structural features and analysis of vascular trees, including scale, orientation, and branching points, using statistical models and principal component analysis to improve accuracy and completeness of vessel structure representation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional image processing techniques are used to extract geometry from medical images, then the process is simple and fast, but the extracted geometry is incomplete and unsuitable for further analysis
Solution Approach 1:
The patent segments the vessel structure extraction process into multiple specialized stages: initial segmentation to identify vessel regions, refinement segmentation to improve boundary accuracy, and hierarchical segmentation to capture both global and local geometric features. This multi-stage segmentation approach enables complete and accurate geometry extraction while managing computational complexity through organized processing steps.
Solution Approach 2:
The patent transforms 2D image data into 3D geometric representations by reconstructing vessel structures in three-dimensional space. This dimensionality change allows extraction of comprehensive geometric parameters including volume, surface area, and spatial orientation that cannot be obtained from 2D images alone, thereby improving measurement precision for diagnostic analysis.
2Loss of time
If manual visual inspection of 2D image slices is performed to understand 3D structure, then no complex processing is needed, but the process is time consuming and perceptually difficult
Solution Approach 1:
The patent replaces manual visual inspection with automated computer-based image processing systems that perform geometric extraction, segmentation, and 3D reconstruction. This substitution eliminates the time-consuming and error-prone manual process while providing consistent, quantitative measurements through algorithmic processing of medical images.
Solution Approach 2:
The patent transforms qualitative visual assessment into quantitative geometric parameters by extracting measurable attributes such as vessel diameter, length, curvature, and branching angles. This parameter transformation enables objective analysis of 3D vascular structures, replacing subjective visual interpretation with precise numerical data for diagnostic purposes.
3Adaptability or versatility
If conventional segmentation techniques are used to identify structures in images, then the process is simple, but the results are unsatisfactory when structures appear at arbitrary locations, sizes and orientations
Solution Approach 1:
The patent implements dynamic segmentation parameters that automatically adapt to the specific characteristics of each vessel structure, including its location, size, and orientation. The segmentation algorithm adjusts its parameters based on local image features and vessel morphology, enabling accurate detection of structures regardless of their arbitrary positions or orientations in the medical images.
Data Source
AI summary
Techniques for linking geometry extracted from one or more medical images, the geometry including a plurality of geometric objects each having parameter values including at least one value for location and at least one value for direction/orientation, the plurality of geometric objects comprising a target geometric object and at least two candidate geometric objects, the techniques include: (A) comparing parameter values of the target geometric object with parameter values of the at least two candidate geometric objects, (B) selecting one of the at least two candidate geometric objects to link to the target geometric object based, at least in part, on the comparison; and (C) linking the to target geometric object with the selected candidate geometric object.