Ultrasound Tissue Quantification Using Intervening Tissue Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Ultrasound imaging of soft tissue, such as liver imaging, faces challenges in accurately quantifying characteristics like elasticity, shear transmission, and fat fraction due to variability in measuring angles and distances caused by intervening tissue layers, leading to miscalculation and less accurate quantification compared to magnetic resonance methods.
Innovation Solution
Intervening tissue layers are measured and integrated into a machine-learned model to quantify ultrasound-derived fat fraction (UDFF), with automatic ROI placement guided by anatomy detection and field of view alignment to improve accuracy and reduce variability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If manual measurement or visual approximation of distances and angles is used, then workflow is simpler, but measurement precision deteriorates leading to undesired variability in quantification
Solution Approach 1:
The system automatically performs measurements of distances and angles using the detected anatomy and field of view information, eliminating the need for manual measurement by operators. The processor autonomously calculates the required parameters based on image data, thereby maintaining workflow simplicity while achieving high measurement precision.
Solution Approach 2:
The patent replaces manual mechanical measurement methods with an automated image processing system that uses computer vision and algorithmic calculation. The processor analyzes anatomical landmarks and field of view parameters to automatically determine distances and angles, substituting human-operated mechanical measurement tools with an automated computational system.
2Measurement precision
If automatic ROI placement is implemented, then measurement precision improves, but device complexity increases
Solution Approach 1:
The processor performs multiple functions including anatomy detection, field of view analysis, automatic ROI placement, and measurement calculation within a single integrated system. This multi-functionality allows the system to achieve high measurement precision through automatic ROI placement without proportionally increasing device complexity, as one component handles multiple critical tasks.
Solution Approach 2:
The system uses detected anatomy and field of view information as intermediary elements to guide automatic ROI placement. These intermediaries serve as reference frameworks that the processor uses to automatically position the region of interest, reducing the need for complex direct control mechanisms while improving placement accuracy.
3Device complexity
If effects of intervening tissue are not accounted for, then device complexity is lower, but quantification accuracy deteriorates
Solution Approach 1:
The system performs preliminary detection and measurement of intervening tissue characteristics before final quantification of the target tissue. By measuring the thickness and properties of intervening layers in advance, the processor can compensate for their effects on ultrasound signal propagation, thereby improving quantification accuracy without requiring overly complex real-time correction mechanisms.
Solution Approach 2:
The system uses the measured characteristics of intervening tissue as feedback to adjust the quantification of target tissue properties. The processor incorporates information about intervening tissue thickness and composition into the calculation algorithm, using this feedback to correct for signal attenuation and other effects, thereby achieving accurate quantification while maintaining manageable system complexity.
Data Source
Figure 1
Figure 2~3
AI summary
In one approach, quantitative ultrasound imaging is altered to account for the effects of intervening tissue (210). The tissue layers between the transducer (320) and the region (250) are measured, and the measurement is input to a machine-learned model (355) to quantify (140) from signals for the region of interest (250) and the measurement. This may provide more accurate quantification. In another approach, the region of interest (250) (ROI) is automatically placed (120), such as through detection (110) of anatomy (e.g., liver capsule), identification of and/or guidance (100) to the field of view, and/or scoring of imaging of the anatomy. This ROI placement (120) may avoid variability in quantification.