Ultrasound Image Data Linking via Deformability Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current ultrasound imaging methods face challenges in accurately linking ultrasound image data with other image data, such as mammography or tomosynthesis data, especially in deformable media like the breast, leading to difficulties in lesion identification and localization during interventional procedures.
Innovation Solution
The method estimates deformability properties of the medium using ultrasound data and links ultrasound image data with other image data based on these properties, employing techniques like block-matching algorithms and finite element modeling to create a simulated deformed medium that matches the deformation state of the other image data, thereby correlating and matching the images for improved accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If ultrasound imaging is performed on a breast that has been deformed during mammography/tomosynthesis, then the lesion location cannot be reliably predicted, but the breast cannot be physically constrained during ultrasound exam
Solution Approach 1:
A virtual model of the breast acts as an intermediary between the physical breast and the imaging systems. This virtual model captures the breast's anatomy and deformation characteristics, allowing the system to predict lesion locations accurately without requiring physical constraint of the breast during ultrasound examination.
Solution Approach 2:
The system creates a virtual copy (digital twin) of the breast that replicates its anatomical structure and deformation properties. This virtual replica allows the system to simulate and predict lesion locations based on mammography/tomosynthesis data without affecting the actual physical breast during ultrasound examination.
2Reliability
If the breast is squeezed between two plaques during mammography/tomosynthesis, then early cancers and microcalcifications can be detected, but the breast and lesion are deformed making localization difficult during ultrasound
Solution Approach 1:
The system performs preliminary creation of a virtual breast model using mammography/tomosynthesis data before the ultrasound examination. This pre-modeled virtual representation captures the breast's anatomy and deformation state, enabling accurate lesion localization predictions before the actual ultrasound scanning begins.
Solution Approach 2:
The virtual model serves as an intermediary that bridges the deformation caused by mammography compression and the ultrasound examination. It allows the system to translate findings from the compressed mammography state to the uncompressed ultrasound state accurately, maintaining both detection reliability and location precision.
3Measurement precision
If manual linking of ultrasound image data with other image data is performed, then operator expertise is required, but the process is time-consuming and less reproducible
Solution Approach 1:
The system performs self-service by automatically linking ultrasound image data with other imaging modalities using the virtual breast model. This automated process eliminates the need for manual operator intervention, reducing processing time while maintaining high accuracy through algorithm-based alignment and registration.
Solution Approach 2:
The system replaces the mechanical/manual process of image data linking with an automated computational approach. Using virtual modeling and algorithmic registration, the system automatically aligns and correlates image data from different modalities, substituting manual expertise with automated processing that is both faster and more reproducible.
Data Source
AI summary
The disclosure relates to a method of linking ultrasound image data associated with a medium with other image data associated with the medium. The method comprises: estimating deformability properties of the medium based on the ultrasound data and linking the ultrasound image data with the other image data based on the deformability properties.