Ultrasound Imaging Parameter Tuning With Machine-Learned Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current ultrasound imaging systems face challenges in achieving consistent diagnostic image quality across diverse patient types, anatomies, and user preferences, leading to increased examination time, operator fatigue, and reduced diagnostic confidence due to the need for manual tuning of imaging parameters.
Innovation Solution
A machine-learned network is employed to optimize imaging parameters based on patient-specific data, user preferences, and regional variations, automating the tuning process to enhance image quality and reduce examination time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual tuning of imaging parameters is performed for each patient, then diagnostic image quality is improved, but examination time increases and operator fatigue increases
Solution Approach 1:
The imaging system automatically adjusts imaging parameters by analyzing the captured image and patient information through a machine-learned network, eliminating the need for manual operator tuning. The system serves itself by autonomously optimizing settings based on real-time feedback from image quality assessment and patient-specific data.
Solution Approach 2:
The system implements a feedback loop where the captured image is analyzed to assess quality, and this information is fed back to automatically adjust imaging parameters. The machine-learned network uses the initial image and patient information to determine optimized settings, which are then applied to improve subsequent images without requiring manual intervention.
2Loss of time
If factory presets are used for different patient types, then setup time is reduced, but image quality cannot be optimized for individual patient variability and user preferences
Solution Approach 1:
The system transitions from static factory presets to dynamic, real-time parameter optimization. Instead of relying on pre-configured settings that cannot adapt to individual variations, the system continuously adjusts imaging parameters based on the specific patient's anatomy, the captured image characteristics, and user preferences, making the optimization process adaptive and flexible.
Solution Approach 2:
The system automatically modifies multiple imaging parameters including frequency, focus, depth, and other settings based on analysis of patient information and image quality. The machine-learned network determines the optimal combination of parameters for each specific case, enabling precise customization without manual intervention.
3Extent of automation
If anatomy-focused segmentation is used to set imaging parameters, then some automation is achieved, but expert review is still required and user preferences are not addressed
Solution Approach 1:
The system fully automates the parameter setting process by using a machine-learned network that analyzes both the image and patient information to determine optimal settings. This eliminates the need for expert review entirely, as the system independently makes all parameter adjustments based on learned patterns and real-time data.
Solution Approach 2:
The machine-learned network serves multiple functions: it performs anatomy recognition, image quality assessment, parameter optimization, and user preference integration all in one unified system. This multi-functional approach replaces the need for separate expert review processes while addressing diverse patient types and user preferences simultaneously.
Data Source
AI summary
Machine learning network trained to tune settings and optimize images. In accordance with one aspect, a method is provided for image optimization with a medical ultrasound scanner. A medical ultrasound scanner images a patient using first settings. A first image from the imaging using the first settings and patient information for the patient are input to a machine-learned network. The machine-learned network outputs second settings in response to the inputting of the first image and the patient information. The medical ultrasound scanner re-images the patient using the second settings. A second image from the re-imaging is displayed.