Medical Image Contrast Tracking for Local Blood Flow Velocity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for computing blood flow velocity in the cardiovascular system fail to accurately measure the velocity in specific sections of blood vessels, particularly at bifurcations, leading to inaccuracies in lesion diagnosis and treatment planning.
Innovation Solution
A method involving user selection of points on a medical image, extraction of blood vessel regions using machine learning, and determination of frame images based on pixel intensity changes to calculate blood flow velocity between selected points.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If average blood flow velocity is calculated in the cardiovascular system, then the overall blood flow characteristics can be obtained, but the blood flow velocity in specific sections (especially at bifurcations) cannot be accurately measured
Solution Approach 1:
The patent divides the cardiovascular system into multiple selectable sections or regions of interest. Users can select specific segments (e.g., individual blood vessels or bifurcation points) to calculate blood flow velocity separately, rather than computing a single average for the entire system. This segmentation enables precise measurement of local blood flow characteristics while maintaining system manageability.
Solution Approach 2:
The system implements location-specific blood flow velocity calculation by allowing users to define particular regions or points within the cardiovascular system. Each selected region undergoes independent analysis, providing locally-optimized measurement precision for critical areas such as bifurcations, while preserving the overall system structure.
2Measurement precision
If blood flow velocity is measured at specific sections using traditional methods, then local velocity data can be obtained, but the measurement accuracy remains insufficient due to inability to track contrast agent movement precisely
Solution Approach 1:
The patent utilizes changes in pixel intensity (analogous to color changes) to track the movement of contrast agent through the blood vessels. By monitoring the temporal and spatial variations in pixel intensity values, the system can precisely determine contrast agent position and calculate blood flow velocity at specific sections without losing critical tracking information.
Solution Approach 2:
The system creates a digital representation or model of contrast agent movement by analyzing sequential medical images. This virtual copy of the physical contrast agent trajectory enables accurate velocity calculation while preserving all movement information, effectively eliminating information loss during the measurement process.
3Loss of information
If the cardiovascular system is analyzed as a whole, then comprehensive blood flow data is obtained, but the blood flow velocity gap between branch vessels and main vessels is not identified
Solution Approach 1:
The patent enables selective segmentation of the cardiovascular system into main vessels and branch vessels, allowing independent analysis of each segment. This reveals local blood flow variations and velocity differences that would be obscured in a whole-system average calculation, while maintaining diagnostic efficiency through targeted analysis of clinically relevant regions.
Solution Approach 2:
The system changes the analysis parameter from global average velocity to local section-specific velocity. By adjusting the spatial scale and measurement location parameters, the system can identify and quantify blood flow velocity variations between different vascular segments, providing comprehensive information without sacrificing diagnostic productivity.
Data Source
AI summary
A method comprises receiving a user input to select a first point and a second point from a medical image, extracting a plurality of blood vessel regions from a plurality of frame images of the medical image, determining a plurality of first regions associated with the first point and a plurality of second regions associated with the second point, determining a first frame image and a second frame image with the contrast agent arriving at the first point and the second point, based on a change in pixel intensity for each of the plurality of first regions and the plurality of second regions, and computing the blood flow velocity from the first point to the second point based on a time interval between the first frame image and the second frame image and on a distance between the first point and the second point.