Template Matching for Irregular Fiducial Marker Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In radiotherapy, the precise tracking of irregularly shaped fiducial markers, such as Visicoil markers, in X-ray images is challenging due to their unpredictable shape and varying orientations, which complicates accurate tumor targeting and normal tissue dose management.
Innovation Solution
An image processing method involving the enhancement of input images, application of low-pass filters, and forward projection of voxels from volumetric images to generate template images, allowing for robust tracking and matching of markers across different orientations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional template matching is used for tracking fiducial markers, then simple shaped markers (like gold cylinders) can be tracked accurately, but irregular shaped markers (like Visicoil) cannot be tracked robustly due to their varying shapes and orientations
Solution Approach 1:
The patent applies dynamics by making the template adaptable to different marker orientations and shapes. Instead of using a fixed static template, the system dynamically adjusts the template based on the actual marker appearance in the image, allowing it to accommodate irregular shapes like Visicoil markers that coil up in unpredictable configurations
Solution Approach 2:
The patent changes key parameters of the template including its shape, orientation, and size to match the observed marker. By allowing these parameters to vary rather than being fixed, the system can track markers with irregular and unpredictable shapes while maintaining tracking accuracy
2Measurement precision
If image processing is applied to enhance marker visibility, then tracking accuracy improves, but processing time and computational complexity increase
Solution Approach 1:
The patent performs preliminary actions by pre-processing the image to enhance marker visibility before template matching. This includes applying filters and enhancement techniques to improve the signal-to-noise ratio and make the marker more distinguishable, which facilitates more accurate tracking in subsequent processing steps
3Manufacturing precision
If forward projection of voxels is used to generate template images from volumetric data, then accurate 3D to 2D transformation is achieved, but computational complexity increases
Solution Approach 1:
The patent replaces complex mechanical or manual template creation processes with computational forward projection. Instead of physically manipulating objects or using complex mechanical systems to generate templates, the system uses algorithmic forward projection of voxels from volumetric images to automatically generate accurate 2D templates
Data Source
AI summary
A method of generating a template image includes: receiving an input from a user representing identifications of an object in different respective slices of a volumetric image; using the input to determine a volume-of-interest (VOI) that includes voxels in a subset of the volumetric image; and determining the template image using at least some of the voxels in the VOI, wherein the act of determining the template image comprises performing a forward projection of the at least some of the voxels in the VOI using a processor. An image processing method includes: obtaining a volumetric image; performing forward projection of voxels in the volumetric image from different positions onto a first plane using a processor; and summing projections on the first plane resulted from the forward projection from the different positions to create a first image slice in the first plane.