Adaptive Calcium Thresholds for Contrast-Enhanced CT Plaque Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for detecting calcified plaques in contrast-enhanced CT scans suffer from high classification errors due to the variability in Hounsfield Unit values caused by the introduction of contrast agents, lacking a standardized calcium assessment threshold.
Innovation Solution
A system and method that dynamically determines a calcium threshold by analyzing local aorta attenuation in CT scans, using mathematical morphology, Gaussian curve fitting, and derivative analysis to identify the optimal threshold for precise plaque detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Illumination intensity
If contrast agents are administered to enhance blood vessel visualization, then image quality for specific purposes is improved, but HU value variability is introduced and calcium measurement standardization is compromised
Solution Approach 1:
The patent applies dynamics by transitioning from a static, fixed calcium threshold (e.g., 130 HU) to a dynamic threshold that automatically adapts to the specific HU value distribution in each CE-CT scan. The system calculates a new threshold based on the actual contrast enhancement level, making the measurement precision adaptive rather than rigid, thus resolving the contradiction between improved image quality and maintained measurement accuracy.
Solution Approach 2:
The patent changes the parameter of calcium detection threshold from a fixed value to a variable value that depends on the contrast agent concentration and scan-specific HU distribution. By adjusting the threshold parameter dynamically according to the actual scan conditions, the system maintains measurement precision despite the HU variability introduced by contrast agents.
2Ease of operation
If uniform thresholds are applied for detecting calcified plaques in CE-CT scans, then processing simplicity is maintained, but classification errors increase due to HU value variability
Solution Approach 1:
The patent performs preliminary analysis of the HU value distribution within the aorta volume before applying the calcium detection threshold. By pre-calculating the mean and standard deviation of HU values in the aorta and using these statistics to determine an adaptive threshold, the system prepares the necessary parameters in advance, maintaining operational simplicity while significantly improving classification accuracy.
Solution Approach 2:
The system performs self-service by automatically determining the appropriate calcium threshold based on the scan-specific HU distribution without requiring manual intervention or external reference. The algorithm self-adjusts to the particular contrast enhancement level and patient characteristics, eliminating the need for complex manual calibration while ensuring high reliability in plaque detection.
3Stability of the object's composition
If fixed calcium threshold values are used, then measurement standardization is maintained, but detection accuracy deteriorates due to contrast agent-induced HU variability
Solution Approach 1:
The patent applies local quality by determining that different regions or conditions require different threshold values. Instead of using a single universal threshold, the system calculates a locally adapted threshold for each scan based on the specific HU distribution characteristics. This allows measurement standardization to be maintained through a systematic approach while achieving high detection accuracy through local adaptation to contrast agent effects.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
System and computer-implemented method of determining a calcium threshold for detecting calcified plaques in computed tomography scans. The method (100) comprises: receiving (110) input images (102) of a CT scan; detecting (120) the aorta (401) in the input images (102), obtaining a volume of interest of the aorta, VOIA (122), formed by a plurality of voxels; performing a mathematical morphology dilation (130) on the VOIA (122), obtaining a volume of interest of the dilated aorta, VOIDA (132); calculating (140) a histogram (142) of the VOIDA (132) including the frequency of voxels per HU value; fitting (150) the histogram (142) to a Gaussian curve (152); computing (160) the derivative (162) of the Gaussian curve (152); and determining (170) a calcium threshold (172) corresponding to the HU value in which the derivative (162) of the Gaussian curve surpasses a threshold (TH) while having a positive slope. The method may further comprise detecting and/or quantifying (180) calcified plaques (182) in a CT scan using the calcium threshold (172).