3D FMBV Ultrasound Quantification With Automatic Depth Compensation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current ultrasound imaging systems lack the ability to accurately and automatically quantify fractional moving blood volume (FMBV) and vascular impedance from three-dimensional and four-dimensional ultrasound volumes, relying heavily on manual adjustments that introduce subjectivity and operator variability.
Innovation Solution
A method and system utilizing a neural network for image enhancement and segmentation, combined with 3D-FMBV analysis algorithms, to automatically calculate FMBV and impedance from power Doppler ultrasound data, including automatic setting adjustments and data partitioning to compensate for depth attenuation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual adjustments are used for FMBV quantification, then operator flexibility is maintained, but subjectivity and operator variability increase
Solution Approach 1:
The system performs automatic image enhancement, segmentation, and FMBV calculation without requiring manual operator intervention. The neural network algorithm autonomously processes ultrasound images, applies appropriate enhancement settings, segments tissues, and computes FMBV values, making the system self-sufficient and eliminating operator variability.
Solution Approach 2:
Manual mechanical adjustments by operators are replaced with an automated computational system using neural networks and image processing algorithms. The mechanical process of manual image adjustment and measurement is substituted with digital automation that consistently applies the same processing rules.
2Reliability
If automatic processing is implemented, then operator variability is reduced, but system complexity increases
Solution Approach 1:
The complex processing task is divided into distinct sequential steps: image enhancement, tissue segmentation, geometric partitioning, and FMBV calculation. Each step is handled by a specialized module in the neural network architecture, making the overall complex system manageable through functional decomposition.
Solution Approach 2:
The neural network system performs multiple functions including image enhancement, tissue segmentation, geometric analysis, and FMBV calculation within a single integrated platform. This multi-functionality consolidates what would otherwise require multiple separate systems into one unified device.
3Area of stationary object
If 3D ultrasound volumes are used, then spatial coverage is improved, but data processing complexity increases
Solution Approach 1:
The system processes three-dimensional ultrasound volume data by transforming it into a series of two-dimensional slices or planes for analysis. This dimensional reduction allows the neural network to process complex 3D volumetric data more efficiently by handling it as multiple 2D images that can be processed with established image processing techniques.
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
Provides accurate, reproducible, and operator-independent quantification of FMBV and vascular impedance, enhancing image quality and reducing human error in ultrasound assessments.
Implementation Method 1
When frequency changes (Doppler ultrasound) are incorporated into structural imaging (B-mode ultrasound) it may additionally be used to evaluate blood flow. Changes in the frequency of the ultrasound echo relative to that of insonation can give movement information about interrogated objects; most frequently these are red blood cells within blood vessels.
Implementation Method 2
machine settings and loss of signal with depth of scanning (known as attenuation) influence the measured vascularity/perfusion.
Data Source
AI summary
A method of quantifying a 3D fractional moving blood volume (3D-FMBV) in a tissue volume of a subject uses an ultrasound system. The method includes acquiring images of the tissue volume from a power Doppler scan of the tissue volume, applying image enhancement settings to the images, segmenting an organ, tissue or region thereof from the image data, determining geometric partitions of the segments based on distance from the transducer head of the ultrasound system, and computing a 3D-FMBV using a 3D-FMBV analysis algorithm from the partitions.