Ultrasound Reference Vessel Detection for Absolute Blood Flow
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing power Doppler ultrasound techniques can only provide relative blood flow measurements, which are influenced by tissue attenuation and lack standardization, making it difficult to accurately diagnose conditions requiring absolute blood flow measurements.
Innovation Solution
A computer-implemented method using a fully convolutional neural network to identify a reference vessel and standardize power Doppler values by selecting a vessel with known vascularity, allowing for absolute blood flow measurements through fractional moving blood volume (FMBV) estimation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual identification of reference region is used for standardisation, then some level of normalisation is achieved, but the process is time-consuming and operator-dependent
Solution Approach 1:
The system automatically identifies the reference vessel and performs standardisation without operator intervention. The automated algorithm selects the largest vessel in the region of interest as the reference vessel, eliminating manual identification steps while maintaining measurement accuracy
Solution Approach 2:
The invention changes the approach from manual visual identification to automated parameter-based selection. By using image processing algorithms that automatically detect vessel characteristics (size, location, intensity), the system transforms the standardisation process into a parameter-driven automated procedure
2Ease of operation
If power Doppler ultrasound is used to measure blood flow, then non-invasive measurement is achieved, but only relative blood flow information is obtained due to unknown attenuation
Solution Approach 1:
The invention introduces a reference vessel as an intermediary element. This reference vessel serves as a mediator that provides known attenuation characteristics, allowing the system to calculate and correct attenuation effects on other vessels in the region, thereby enabling absolute blood flow measurements while maintaining non-invasive operation
Solution Approach 2:
The system measures blood flow in a larger region of interest that includes both the target vessels and a reference vessel. By intentionally including extra vascular structures in the measurement region, the system obtains sufficient information to perform attenuation correction and derive absolute flow values
3Productivity
If automated vessel identification is implemented, then standardisation time is reduced, but algorithm complexity increases
Solution Approach 1:
The automated identification process is divided into distinct sequential steps: region of interest segmentation, vessel detection within the segmented region, reference vessel selection based on size criteria, and standardisation parameter calculation. This segmentation of the algorithm into modular steps manages complexity while maintaining high automation speed
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables robust, automated, and accurate absolute blood flow measurements, reducing variability and noise sensitivity, and facilitating quantitative comparisons between patients, improving diagnosis of conditions like fetal growth restriction and pre-eclampsia.
Implementation Method 1
Power Doppler ultrasound is a technique that uses the amplitude of reflected signals as a function of frequency shift relative to the emitted signal to determine movement of tissue in a subject, in particular blood flow
Implementation Method 2
this PD signal representing the local concentration of red blood cells (which scatter ultrasound)
Data Source
AI summary
A computer-implemented method of automatically identifying a reference vessel in an ultrasound image, the method comprising: segmenting the image to identify an organ; locating a predetermined anatomical landmark specific to the organ; identifying appropriate vasculature for the organ; and selecting a reference vessel from the vasculature that has a size within a predetermined size range and a location with a predetermined distance range from the predetermined interface.