3D Marker Segmentation in Cone-Beam CT via Volumetric Modeling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Reliable segmentation of irregularly shaped radiopaque markers in x-ray images is challenging due to varying orientations and directions in cone-beam CT scans, which complicates precise target localization in radiotherapy.
Innovation Solution
A method and system for constructing a three-dimensional model of markers using binary images obtained from projection images, employing a processing unit to determine voxels in a three-dimensional space, which collectively indicate the marker's shape, through techniques like ray tracing and alignment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If markers are viewed from varying directions in cone-beam CT scan, then more comprehensive three-dimensional information is obtained, but segmentation reliability deteriorates due to irregular shapes and varying orientations
Solution Approach 1:
The patent transforms the segmentation problem from two-dimensional projection images to three-dimensional space by constructing a volumetric model using voxels. This dimensional transformation allows the system to recover and represent the complete three-dimensional shape of markers regardless of their orientation or rotation in the projection images, thereby maintaining segmentation reliability while utilizing information from multiple viewing angles.
Solution Approach 2:
The patent creates a digital three-dimensional copy of the marker using a grid of voxels that represents the marker's shape in three-dimensional space. This virtual model can be rotated and oriented to match any viewing angle, allowing reliable segmentation without being constrained by the varying orientations present in the projection images.
2Measurement precision
If binary images are determined from projection images for three-dimensional model construction, then segmentation accuracy is improved, but processing complexity increases
Solution Approach 1:
The patent divides the three-dimensional space into a grid of discrete volumetric elements (voxels). Each voxel can be independently determined to contain marker material or not, based on the binary images from projection data. This segmentation approach simplifies the representation of complex marker shapes while maintaining high segmentation accuracy.
Solution Approach 2:
The patent replaces complex mechanical or manual segmentation processes with an automated computational approach. By using algorithms to determine voxel states from binary images, the system achieves high segmentation accuracy while reducing the need for manual intervention or complex mechanical measurement devices.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enables accurate three-dimensional modeling of markers, improving their segmentation and localization, thereby enhancing the precision of radiotherapy by reducing artifacts and motion-induced errors in image-guided treatments.
Implementation Method 1
x-ray visible markers may be implanted in or near a tumour. It allows use of the projected marker trajectory in x-ray images for image-guided radiotherapy (IGRT)
Data Source
AI summary
A method of determining a model of a marker includes obtaining projection images, each of the projection images having an image of a marker that indicates a shape of the marker, determining binary images of the marker for respective ones of the projection images, and constructing a three-dimensional model of the marker using the binary images, the three-dimensional model comprising a set of voxels in a three-dimensional space that collectively indicates a three-dimensional shape of the marker, wherein the act of constructing the three-dimensional model is performed using a processing unit.