Closed Surface Fitting for Orthopedic Image Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current surgical joint repair procedures face challenges in accurately determining the size and shape of anatomical objects, such as the humeral head, due to limitations in imaging modalities like CT scans, which can result in imperfect boundaries and blurring between anatomical objects, affecting prosthetic selection and surgical planning.
Innovation Solution
The use of closed surface fitting (CSF) techniques for segmentation of 3D image information to generate a mask that accurately identifies anatomical objects, allowing for precise determination of their size, shape, and location, enabling better surgical planning and prosthetic selection by iteratively fitting a closed surface shape to the image data and determining corresponding points based on normal vectors and intensity changes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If voxel-based separation is used to determine boundaries between anatomical objects, then some level of separation can be achieved, but the boundaries become imperfect with gaps where separation is unclear
Solution Approach 1:
The patent introduces a closed surface model as an intermediary between the raw voxel data and the final boundary determination. This model acts as a mediator that fills in the gaps and uncertainties in the voxel-based separation by providing a continuous geometric representation that interpolates missing boundary information.
Solution Approach 2:
The patent transforms the discrete voxel intensity data into continuous geometric parameters by fitting a closed surface model. This parameter transformation changes the nature of the boundary representation from discrete and uncertain to continuous and deterministic, resolving the reliability issue.
2Loss of information
If standard imaging modalities like CT scans are used, then anatomical objects can be visualized, but the resolution limitations cause blurring and imperfect boundaries between objects
Solution Approach 1:
The patent performs preliminary segmentation and boundary identification using available imaging data before the actual measurement and analysis. By pre-identifying candidate boundaries and using them to initialize the closed surface model, the system recovers boundary information that would otherwise be lost due to resolution limitations.
Solution Approach 2:
The patent creates a geometric copy or model of the anatomical objects using closed surface representations. This model copy preserves and enhances the boundary information that is degraded in the original imaging data, allowing for precise measurements without being constrained by the original resolution limitations.
3Measurement precision
If iterative closed surface fitting is performed to improve boundary accuracy, then anatomical object boundaries become more precise, but the computational complexity and processing time increase
Solution Approach 1:
The patent performs preliminary actions to initialize the closed surface model with candidate boundaries from voxel-based separation and other imaging data. This pre-initialization provides a good starting point for the iterative fitting process, reducing the number of iterations needed and thereby lowering computational complexity while maintaining precision.
Solution Approach 2:
The patent implements feedback mechanisms in the iterative closed surface fitting process where the model is continuously refined based on how well it matches the observed imaging data. This feedback-driven approach ensures that the complexity of the iterative process is justified by the progressive improvement in boundary precision, stopping when adequate accuracy is achieved.
Data Source
AI summary
Techniques are described for closed surface fitting (CSF). Processing circuitry may determine a plurality of points on a shape, determine a contour, used to determine a shape of an anatomical object, from image information of one or more images of a patient, and determine corresponding points on the contour that correspond to the plurality of points on the shape based on at least one of respective normal vectors projected from points on the shape and normal vectors projected from points on the contour. The processing circuitry may generate a plurality of intermediate points between the points on the shape and the corresponding points on the contour, generate an intermediate shape based on plurality of intermediate points, and generate a mask used to determine the shape of the anatomical object based on the intermediate shape.