Cardiac Calcification Tracking Centerline Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current cardiac diagnostics techniques fail to accurately detect the centerline of the lumen in coronary arteries due to interference from cardiac calcifications, leading to unreliable lumen visualization and stenosis measurements.
Innovation Solution
A method and system that utilize intravascular ultrasound views to segment the coronary tree, compute mean sub-volumes, perform gray value segmentation, and define a centerline that avoids calcifications, enhancing lumen visualization by separating the lumen, vessel wall, and calcified plaque.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If current centerline detection techniques are used, then the centerline can be detected, but it detects the centerline inside cardiac calcifications instead of the actual lumen center, causing unreliable lumen visualization and stenosis measurement
Solution Approach 1:
The patent extracts and removes calcifications from the image data before performing centerline detection. By separating the calcified plaque from the lumen structures, the system can then accurately detect the true lumen centerline without being misled by the high-density calcification signals, thereby resolving the contradiction between detecting centerline and maintaining lumen visualization reliability
Solution Approach 2:
The patent segments the coronary artery structures into distinct components: lumen, vessel wall, and calcified plaque. This segmentation allows the system to process each component separately, enabling accurate centerline detection within the lumen while excluding calcifications from the detection process, thus improving both measurement precision and visualization reliability
2Quantity of substance
If calcifications are present in the coronary artery, then the vascular structure is visualized, but the lumen visualization is upset and stenosis measurement becomes unreliable
Solution Approach 1:
The system extracts calcifications from the imaging data and creates a separate representation of the lumen structure. This allows the lumen to be visualized and measured independently of the calcifications, maintaining accurate stenosis measurement while still detecting the presence and location of calcified plaque
Solution Approach 2:
The patent introduces an intermediary processing step that separates calcification signals from lumen signals. This intermediary process allows both calcifications and lumen to be detected and measured simultaneously without interference, resolving the contradiction between visualizing vascular structure and measuring lumen dimensions accurately
3Productivity
If automatic centerline detection is performed without manual edition, then the process is faster, but the lumen centerline detection becomes unreliable due to calcification interference
Solution Approach 1:
The patent performs preliminary processing to remove or separate calcifications from the image data before automatic centerline detection is performed. This preliminary action ensures that when automatic detection runs, it operates on cleaned data without calcification interference, achieving both speed and reliability without requiring manual edition
Solution Approach 2:
The system performs self-correction by automatically detecting and removing calcifications as part of the processing pipeline. The automatic centerline detection algorithm itself serves to identify and exclude calcified regions, making the system self-sufficient and eliminating the need for manual intervention while maintaining high reliability
Data Source
AI summary
Systems, methods and computer products for automatically extracting automatically cardiac calcifications and obtaining a centerline in the tracking. Exemplary embodiments include a method of cardiac diagnostics, the method including obtaining coronary tree segmentation to obtain cardiac volume information, splitting the volume into portions to obtain an adjacency graph, computing a mean of a sub-volume of the volume, obtaining gray value segmentation of the sub-volume, defining a centerline of a blood vessel that avoids calcifications within the blood vessel and detecting an actual centerline of the blood vessel and enhancing lumen visualization of the blood vessel.