PCAT CT Analysis Without Iodine Confounding for MACE Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current assessments of pericoronary adipose tissue (PCAT) for predicting major adverse cardiovascular events (MACE) are compromised by iodine confounding in post-contrast coronary computed tomography angiography (CCTA) images, leading to inaccurate predictions due to elevated fat attenuation index (FAI) and texture radiomics issues.
Innovation Solution
Utilizing non-confounding PCAT features extracted from low-dose computed tomography calcium score (CTCS) images, which are free from iodine confounding, to generate a regression model for predicting MACE, incorporating intensity, morphology, and texture features.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If post-contrast CCTA images are used to assess PCAT for MACE prediction, then comprehensive vascular information is obtained, but iodine confounding occurs leading to elevated FAI and inaccurate predictions
Solution Approach 1:
The patent extracts and removes the harmful iodine confounding effect from the PCAT assessment by using non-contrast CT images instead of post-contrast CCTA images. This extraction approach eliminates the source of measurement error while preserving the ability to assess PCAT characteristics for MACE prediction.
Solution Approach 2:
The patent introduces non-contrast CT images as an intermediary medium to assess PCAT features without the interfering presence of iodine contrast. This intermediary approach allows measurement of PCAT density and texture characteristics that are not confounded by iodine enhancement.
2Measurement precision
If FAI measurement is performed on post-contrast CCTA images, then PCAT assessment is conducted, but measurement precision deteriorates due to iodine confounding
Solution Approach 1:
The patent extracts and eliminates the iodine confounding factor from the measurement process by utilizing non-contrast CT images. This removal of the harmful element restores measurement precision for FAI and other PCAT characteristics.
Solution Approach 2:
The patent changes the imaging parameter from post-contrast to non-contrast CT acquisition, thereby altering the physical state of the imaging process to eliminate iodine enhancement effects. This parameter change restores accurate measurement of PCAT density values.
3Reliability
If texture radiomics are extracted from post-contrast CCTA images, then comprehensive PCAT characterization is achieved, but prediction accuracy decreases due to iodine artifacts
Solution Approach 1:
The patent converts the absence of iodine contrast from a potential limitation into a benefit by eliminating texture artifacts and enhancement variability. This allows extraction of pure, unconfounded texture radiomics features that more accurately reflect underlying PCAT pathology.
Solution Approach 2:
The patent uses non-contrast CT images as an intermediary to obtain clean texture radiomics data without iodine interference. This intermediary approach preserves the full range of PCAT texture characteristics for machine learning analysis.
Data Source
AI summary
The present disclosure, in some embodiments, relates to a method of generating a prognosis for a patient. The method includes accessing automatically segmented pericoronary adipose tissue (PCAT) corresponding to a patient within an electronic memory. A plurality of non-confounding PCAT features are generated by measuring values of Hounsfield units for an imaging unit within the PCAT. The measured values of the Hounsfield units are predominately free of iodine confounding and artifacts. The plurality of non-confounding PCAT features are provided to a regression model. The regression model is configured to generate a prognosis for the patient using the plurality of non-confounding PCAT features