Material-Property Templates for Target Tracking in Radiation Therapy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional radiation therapy methods face challenges in accurately tracking moving target structures due to patient motion, particularly when relying on implanted fiducial markers, which can migrate and become unreliable, leading to inaccuracies in dose delivery and healthy tissue sparing.
Innovation Solution
A template-based, markerless approach for target structure tracking is implemented using material properties such as density and effective atomic number, generating templates from planning images and matching them with real-time treatment images using AI engines to improve positional verification and dose accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If implanted fiducial markers are used for target structure tracking, then tracking can be performed during radiation therapy, but the markers may migrate and become unreliable
Solution Approach 1:
The patent extracts the tracking function from physical implanted markers and transfers it to naturally occurring anatomical structures. By using AI-based image analysis to identify and track anatomical landmarks (such as bone structures, organ contours) directly from imaging data, the system eliminates the need for foreign body implants while maintaining tracking capability throughout the treatment process.
Solution Approach 2:
The patent creates a digital copy of the target structure and surrounding anatomy through AI-based image processing. Templates are generated from planning CT scans and continuously matched against treatment images to track positional changes. This digital twin approach allows reliable tracking without physical markers that could migrate.
2Measurement precision
If conventional template matching is used, then target structure tracking is achieved, but tracking accuracy is insufficient due to motion
Solution Approach 1:
The patent transforms the template matching process from simple pixel intensity comparison to multi-parameter analysis including material density, effective atomic number, and anatomical feature geometry. By incorporating these additional parameters, the AI system can distinguish between actual target motion and imaging artifacts, significantly improving tracking accuracy during patient motion.
Solution Approach 2:
The patent combines multiple imaging modalities and analysis techniques into a composite tracking system. It integrates CT density information, atomic number data, and AI-based anatomical recognition to create a robust tracking framework that maintains accuracy despite patient motion and positioning variations.
3Object-affected harmful factors
If markerless approach using material properties is used, then invasive procedures are eliminated, but tracking requires complex image processing
Solution Approach 1:
The patent enables the imaging system to perform its own tracking function by analyzing its existing output data. The AI engine processes the CT and treatment images already acquired for treatment planning and delivery, extracting tracking information without requiring separate imaging systems or additional patient preparations. This self-service approach eliminates invasive marker implantation while using readily available imaging data.
Data Source
AI summary
Example methods and systems for template generation and target structure tracking are described. In one example, a computer system may obtain (a) planning image data that is associated with a target structure of a patient requiring radiation therapy, or (b) transformed image data that is generated based on the planning image data. Based on the planning image data and/or the transformed image data, the computer system may generate first material property data that represents a particular material property associated with the target structure. Based on the first material property data, the computer system may generate a template that represents the particular material property. The template may be generated to be matchable against second material property data that also represents the particular material property for tracking the target structure during a treatment phase.