AI Ultrasound Parameter Optimization for Image Quality

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Medical ultrasound imaging faces challenges in achieving consistent high-quality images due to subjective adjustment of acquisition and post-acquisition parameters, leading to irreproducible results and suboptimal image quality.

Innovation Solution

An automated image quality measurement algorithm using artificial intelligence to optimize acquisition parameters sequentially and apply optimal post-acquisition processing parameters, based on machine learning models for depth and frequency, to select parameter values that result in high image quality.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual adjustment of acquisition and post-acquisition parameters is used, then operator flexibility is maintained, but image quality consistency deteriorates and results become irreproducible

Engineering Contradiction:

Improveimage quality consistencyVSAvoidparameter optimization system

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system automatically optimizes acquisition parameters and post-acquisition processing parameters without requiring manual intervention. The AI-based algorithm independently analyzes ultrasound images, determines optimal parameters, and applies them consistently across exams, eliminating operator-dependent variability while maintaining high image quality consistency.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system incorporates feedback loops where image quality metrics are continuously monitored and used to adjust parameter selections. The AI algorithm analyzes the impact of different parameter values on image quality and iteratively refines parameter optimization based on observed results, ensuring consistent high-quality images across multiple exams.

Inventive Principle:

Principle #23Feedback

2Reliability

If multiple parameter values are tested to optimize image quality, then image quality improves, but exam time increases

Engineering Contradiction:

Improveimage qualityVSAvoidexam time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs parameter optimization in advance before actual diagnostic imaging. By pre-determining optimal acquisition and post-acquisition parameters using AI algorithms, the system eliminates the need for time-consuming manual parameter adjustment during exams, allowing operators to proceed directly with diagnostic imaging using already-optimized settings.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces manual mechanical parameter adjustment with automated AI-based parameter selection. Instead of operators manually testing multiple parameter values, the system uses machine learning models to automatically identify optimal parameters, significantly reducing the time required for parameter optimization while maintaining or improving image quality.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Reliability

If automated AI algorithm is applied, then image quality consistency improves, but system complexity increases

Engineering Contradiction:

Improveimage quality consistencyVSAvoidautomated parameter selection system

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The AI-based parameter optimization system is designed to be universally applicable across different ultrasound exams, anatomical regions, and operator skill levels. The same algorithm handles parameter optimization for various imaging scenarios, making the system versatile while maintaining consistent image quality without requiring separate complex systems for different applications.

Inventive Principle:

Principle #6Universality (Multi-functionality)

4Device complexity

If sequential parameter selection is used, then parameter optimization is simplified, but number of images required for analysis increases

Engineering Contradiction:

Improveparameter selection processVSAvoidnumber of ultrasound images

Core Design Contradiction:

Device complexityVSQuantity of substance

Solution Approach 1:

The patent segments the parameter optimization process into distinct sequential steps, where one parameter is optimized at a time while others are held constant. This segmentation simplifies the overall optimization process by breaking down complex multi-parameter interactions into manageable steps, allowing the AI algorithm to systematically evaluate parameter impacts without requiring analysis of all possible parameter combinations simultaneously.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS11308609B2System and methods for sequential scan parameter selection

Publication Date: 2022.04.19 GE PRECISION HEALTHCARE LLC

AI summary

Methods and systems are provided for sequentially selecting scan parameter values for ultrasound imaging. In one example, a method includes selecting a first parameter value for the a first scan parameter based on an image quality of each ultrasound image of a first plurality of ultrasound images of an anatomical region, each ultrasound image of the first plurality of ultrasound images having a different parameter value for the first scan parameter, selecting a second parameter value for a second scan parameter based on an image quality of each ultrasound image of a second plurality of ultrasound images of the anatomical region, each ultrasound image of the second plurality of ultrasound images having a different parameter value for the second scan parameter, and applying the first parameter value for the first scan parameter and the second parameter value for the second scan parameter to one or more additional ultrasound images.