3D CT Vessel Segmentation Using Spline Mesh Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for detecting soft plaque in cardiovascular CT datasets are inefficient due to the invasive nature of IntraVascular Ultrasound and the lack of automated processes for distinguishing soft plaque from calcification in non-contrasted CT studies, leading to high volumes of manual data processing and reduced standardization.
Innovation Solution
A method for processing CT datasets that segments 3D objects using a 3D mesh with splines in radial and longitudinal directions, allowing for the detection of vessel contours by adjusting control points based on user input, thereby automating the detection of vessel walls and plaque deposits.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If IntraVascular Ultrasound is used to detect soft plaque, then detection accuracy is improved, but the procedure becomes invasive and can only be performed on symptomatic patients
Solution Approach 1:
The patent uses CT imaging to create a non-invasive copy or surrogate representation of the vascular structure and plaque deposits, replacing the need for invasive IVUS procedures. The system processes CT data to generate 3D visualizations that replicate the diagnostic information previously obtainable only through invasive means.
Solution Approach 2:
The patent introduces an automated image processing system as an intermediary between the CT scan data and the diagnostic interpretation. This intermediary system automatically segments vessels, identifies plaque, and generates measurements, eliminating the need for invasive procedures while maintaining diagnostic accuracy.
2Measurement precision
If manual processing of CT data is performed, then detection of vessel walls and plaque is possible, but productivity is reduced and standardization suffers
Solution Approach 1:
The system enables self-service automated processing where the computer automatically segments vessels, identifies plaque, and generates measurements without requiring manual intervention. The automated methods perform all processing steps independently, dramatically increasing productivity while maintaining consistent diagnostic quality.
Solution Approach 2:
The patent replaces manual mechanical processing methods with automated computational algorithms. Instead of manual review and measurement by radiologists, the system uses automated image processing algorithms to detect vessel walls, segment plaque, and generate diagnostic reports, thereby increasing both speed and standardization.
3Measurement precision
If manual review of CT data is performed, then plaque can be identified, but the volume of data requires extensive processing time
Solution Approach 1:
The system performs preliminary automated segmentation and identification of vessels and plaque before final diagnostic interpretation. By pre-processing the data to identify key features and generate initial measurements, the system reduces the time required for manual review while maintaining accurate plaque identification.
Data Source
AI summary
Method and system for processing an object within a diagnostic image comprises segmenting a three dimensional (3D) object within a diagnostic image. A contour of the object is fitted with a 3D mesh comprising splines in at least first and second directions. The splines provide a plurality of editable control points, and the splines in the first direction intersect with the splines in the second direction at intersection points. A position of at least one control point on the 3D mesh is adjusted based on a user input.