2D Ultrasound Cross-Referencing Using Transformation Matrix Alignment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional 2D ultrasound imaging relies on manual manipulation to capture 3D anatomy, leading to inefficient and inconsistent registration of orthogonal views, which is time-consuming and places high cognitive load on radiologists, resulting in variability and incorrect diagnoses.
Innovation Solution
A method and system for cross-referencing 2D ultrasound scans by generating orthogonal views and using correspondence transformation matrices to align pixel positions, enabling automated registration of 2D ultrasound images.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If two orthogonal sweeps of 2D ultrasound images are taken to capture 3D anatomy, then imaging resolution is improved, but the time required for mental cross-referencing and registration increases
Solution Approach 1:
The system creates a synthetic 2D representation of the target anatomy from the first sweep by projecting 3D volumetric data generated from the second sweep. This synthetic copy allows automatic alignment and cross-referencing between the two orthogonal views without requiring manual mental registration, thus resolving the time loss while maintaining high imaging resolution
Solution Approach 2:
The patent replaces the mechanical/mental process of manual image registration with an automated computational system. The system automatically determines correspondence transformation matrices and aligns pixel positions across different views using image processing algorithms, eliminating the time-consuming manual cross-referencing process
2Ease of operation
If freehand ultrasound sweeping is used to obtain 2D images, then ease of operation is improved, but image registration and matching becomes challenging
Solution Approach 1:
The system introduces a synthetic 2D representation as an intermediary between the two orthogonal sweeps. This synthetic representation serves as a common reference framework that automatically aligns the first and second sweeps, resolving the registration difficulty while preserving the ease of freehand operation
Solution Approach 2:
The patent transforms the problem by changing the parameter space from direct pixel-by-pixel registration to transformation matrix-based alignment. By determining correspondence transformation matrices that map pixel positions between views, the system simplifies the registration process while maintaining the flexibility of freehand sweeping
3Reliability
If mental cross-referencing is performed by radiologists, then diagnostic accuracy is maintained, but cognitive load and variability increase
Solution Approach 1:
The system performs self-service by automatically generating the synthetic 2D representation and determining the correspondence transformation matrices without requiring radiologist intervention. This automation maintains diagnostic accuracy through consistent algorithmic processing while eliminating the cognitive load and variability associated with manual cross-referencing
Solution Approach 2:
The patent substitutes the human cognitive process of mental cross-referencing with an automated computational system. The system automatically aligns images, determines correspondence relationships, and provides diagnostic support, thereby reducing cognitive load while maintaining reliable diagnostic accuracy through consistent, repeatable processing
Data Source
AI summary
A method for cross-referencing of 2D ultrasound scans of a tissue volume comprises generating first and second 2D representations of a target anatomy, respectively, from first and second series of 2D ultrasound images of the tissue volume generated. The method includes generating first and second simulated 2D representations of the target anatomy, respectively, from the second and first series of 2D ultrasound images. The 2D and simulated 2D representations are processed to at least substantially match pixel positions in the 2D and simulated 2D representations associated with the target anatomy. The method includes determining first and second correspondence transformation matrices from the processed 2D and simulated 2D representations, and using the first and second correspondence transformation matrices to determine, for a location in the second series of 2D ultrasound images associated with the target anatomy, a corresponding location in the first series of 2D ultrasound images.