FFR Estimation from CT Angiography Using Pixel-Wise Ratio Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current invasive coronary angiography (ICA) is costly and yields limited data, while non-invasive imaging technologies like Coronary Computed Tomography Angiography (CCTA) provide high sensitivity but may not offer real-time, accurate hemodynamic parameter estimation, particularly for fractional flow reserve (FFR) values.
Innovation Solution
A method using deep learning techniques and CT imaging to segment vasculature image data, determining a reference value based on the ascending aorta, and calculating FFR values on a pixel-by-pixel basis to generate an FFR image, which can be displayed quickly and accurately, applicable to various imaging modalities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If invasive coronary angiography (ICA) is used to obtain hemodynamic data, then data can be acquired through direct measurement, but the procedure becomes invasive and costly with limited data value
Solution Approach 1:
The patent replaces the mechanical/invasive measurement system (pressure catheter insertion) with a non-invasive imaging-based computational system. CT imaging captures vascular anatomy and contrast enhancement patterns, while computational algorithms estimate FFR values without physical intrusion into the vascular system, thereby eliminating procedural risks and costs associated with invasive catheterization.
Solution Approach 2:
The patent introduces contrast media as an intermediary substance that enables non-invasive measurement. The contrast agent enhances vascular visibility in CT images and provides the necessary signal for computational FFR estimation, serving as a mediator between the imaging system and the hemodynamic parameters without requiring direct invasive measurement.
2Object-affected harmful factors
If non-invasive imaging technologies like CCTA are used, then patient morbidity is reduced, but real-time accurate hemodynamic parameter estimation is not provided
Solution Approach 1:
The patent segments the vascular system into distinct regions (reference vessel region and vessel region of interest) and processes image data at the pixel level. This segmentation enables precise localization of stenotic lesions and accurate calculation of FFR values for specific vascular segments while maintaining non-invasive imaging benefits.
Solution Approach 2:
The patent transforms anatomical image parameters (pixel intensity values from CT scans) into functional hemodynamic parameters (FFR values). By establishing mathematical relationships between contrast enhancement patterns and blood flow dynamics, the system derives accurate hemodynamic information from non-invasive anatomical imaging data.
3Measurement precision
If traditional FFR measurement methods are used, then clinically-determined values are obtained, but the process is time-consuming and not suitable for real-time decision making
Solution Approach 1:
The patent performs preliminary processing of CT image data during the scanning process itself, extracting vascular geometry and contrast enhancement characteristics. This preliminary action prepares the data for rapid FFR calculation, enabling real-time or near-real-time hemodynamic assessment without requiring separate measurement procedures or prolonged processing times.
Solution Approach 2:
The patent replaces time-consuming mechanical measurement procedures (invasive catheter-based pressure measurements) with rapid computational algorithms that process CT image data. This substitution dramatically reduces measurement time while maintaining clinical accuracy, enabling immediate diagnostic and treatment decisions.
Data Source
AI summary
The present approach relates to determining a reference value based on image data that includes a non-occluded vascular region (such as the ascending aorta in a cardiovascular context). This reference value is compared on a pixel-by pixel basis with the CT values observed in the other vasculature regions. With this in mind, and in a cardiovascular context, the determined FFR value for each pixel is the ratio of CT value in the vascular region of interest to the reference CT value.