AI-Guided Shear Wave Elastography Targeting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current ultrasound imaging technologies face challenges in efficiently targeting and analyzing regions of interest, such as tumors, within large volumes of tissue, leading to increased processing loads and reduced elasticity imaging frame rates.
Innovation Solution
The implementation of an AI-driven method that detects regions of interest within ultrasound images and selectively applies shear wave elastography, reducing the volume of data analyzed and improving image quality by focusing elastography on specific areas.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If shear wave elastography is applied to the entire ultrasound image volume, then comprehensive tissue elasticity coverage is achieved, but processing load increases and frame rate decreases
Solution Approach 1:
The patent segments the ultrasound image volume into multiple regions of interest (ROIs) and applies shear wave elastography selectively to each ROI rather than processing the entire volume. This segmentation approach reduces the total processing load while maintaining comprehensive elasticity measurement coverage across all relevant areas, thereby improving frame rate without sacrificing measurement precision.
2Productivity
If AI model is used to detect regions of interest, then elastography processing is reduced and frame rate improves, but system complexity increases
Solution Approach 1:
The patent introduces an AI model as an intermediary component that automatically detects and identifies regions of interest containing potential tumors. This intermediary AI detection layer simplifies the overall system workflow by automatically selecting ROIs, eliminating the need for complex manual region selection mechanisms, and enabling efficient selective elastography processing that improves frame rate while managing system complexity through automation.
3Productivity
If selective elastography is applied only to detected regions of interest, then processing load is reduced, but coverage of potential tumors may be incomplete
Solution Approach 1:
The patent implements a feedback mechanism where the AI model continuously analyzes ultrasound images, detects potential tumors, and dynamically adjusts the selection of regions of interest for elastography processing. This feedback loop ensures that all areas with potential tumors are identified and included in the selective elastography analysis, maintaining complete tumor detection coverage while preserving processing efficiency through targeted rather than exhaustive processing.
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
This approach enhances the accuracy and quality of elasticity measurements, improves the elasticity imaging frame rate, and directs the attention of physicians to potential tumors, facilitating non-invasive diagnostics.
Implementation Method 1
an ultrasound probe comprising a plurality of transducer elements emits ultrasonic pulses which reflect or echo, refract, or are absorbed by structures in the body
Implementation Method 2
an ultrasound probe comprising a plurality of transducer elements emits ultrasonic pulses which reflect or echo, refract, or are absorbed by structures in the body
Implementation Method 3
an ultrasound probe comprising a plurality of transducer elements emits ultrasonic pulses which reflect or echo, refract, or are absorbed by structures in the body
Implementation Method 4
Shear wave elastography provides a quantitative ultrasound imaging mode, wherein shear waves propagate through tissue, causing transient displacements
Implementation Method 5
The ultrasound probe can measure, via ultrasonic pulses or waves propagating perpendicular to the shear waves, the velocity of these transient displacements
Data Source
AI summary
Various methods and systems are provided for ultrasound imaging. In one embodiment, a method comprises acquiring, with an ultrasound transducer of a scanning apparatus during an ultrasound scan of a patient, an ultrasound image, detecting, with an artificial intelligence model, a region of interest within the ultrasound image including a possible tumor, acquiring, with the ultrasound transducer, an elastic image of tissue within the region of interest, and displaying, with a display device, the elastic image. In this way, shear wave elastography may be automatically targeted to a region of interest, thereby reducing the processing load for the analysis and enabling a higher elasticity imaging frame rate for three-dimensional ultrasound imaging.