Biomechanical Model Deformable Registration of MR and Ultrasound Images
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current image registration techniques for fusing Magnetic Resonance (MR) and Ultrasound (US) images are inadequate due to soft tissue deformation during US imaging, which renders rigid transformations insufficient for accurate alignment of prostate structures, necessitating more sophisticated deformable registration methods.
Innovation Solution
The use of biomechanical models with displacement boundary conditions generated from organ segmentations in MR and US images, where 3D point representations are determined and used to register the images, employing machine learning models for segmentation and a biomechanical tissue model for deformation alignment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If rigid transformation is used to align prostate structures, then the registration process is simple, but accurate alignment cannot be achieved due to soft tissue deformation
Solution Approach 1:
The patent transitions from rigid transformation parameters (translation and rotation only) to deformable transformation parameters that include tissue displacement fields. The biomechanical model introduces additional parameters describing local tissue deformation, allowing the registration to account for soft tissue elasticity and achieve accurate alignment despite tissue deformation during imaging
Solution Approach 2:
The patent introduces a biomechanical tissue model as an intermediary between the two imaging modalities. This model acts as a physical mediator that simulates tissue deformation behavior, bridging the gap between rigid image coordinates and actual deformed tissue positions, thereby enabling accurate registration while maintaining computational tractability
2Measurement precision
If deformable registration using biomechanical models is used, then accurate alignment of prostate structures is achieved, but the device complexity increases
Solution Approach 1:
The patent performs preliminary segmentation of the prostate from both MR and US images to extract 3D surface geometries before registration. This preprocessing step creates simplified geometric representations that serve as input to the biomechanical model, reducing the complexity of the subsequent deformable registration by working with surface meshes rather than full volumetric data
Solution Approach 2:
The patent segments the prostate tissue from surrounding structures in both imaging modalities to isolate the region of interest. This segmentation creates discrete 3D point representations that can be independently processed by the biomechanical model, reducing computational complexity by focusing only on the relevant tissue rather than the entire imaging volume
Data Source
AI summary
A computer-implemented method for performing deformable registration between Magnetic Resonance (MR) and Ultrasound (US) images include receiving an MR volume depicting an organ and segmenting the organ from the MR volume to yield a first 3D point representation of the organ in MR coordinates. Additionally, a US volume depicting an organ is received and the organ is segmented from the US volume to yield a second 3D point representation of the organ in US coordinates. Next, a plurality of point correspondences between the first 3D point representation and the second 3D point representation are determined. Then, a biomechanical model is applied to register the MR volume to the US volume. The plurality of point correspondences are used as displacement boundary conditions for the biomechanical model.