AI Material-Property Tracking for Radiation Therapy Target Structures
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 be unreliable and invasive.
Innovation Solution
A template-based, markerless approach using material properties such as material density or effective atomic number for tracking target structures during radiation therapy, employing AI engines to process image data and generate templates that match these properties for precise positional verification and dose delivery.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If fiducial markers are implanted for target structure tracking, then tracking capability is provided, but patient risk and marker reliability issues arise
Solution Approach 1:
The patent extracts the tracking function from the implanted fiducial marker concept and implements it using intrinsic material properties of the target structure itself. The AI engine processes image data to generate material property data that directly represents the target structure's characteristics, eliminating the need for separate marker implants while maintaining tracking capability.
Solution Approach 2:
The target structure serves its own tracking function through its inherent material properties (density, effective atomic number) rather than requiring external markers. The AI-based system extracts and utilizes these self-contained properties to enable markerless tracking, making the target structure self-sufficient for tracking purposes.
2Measurement precision
If fiducial markers are used for tracking, then target position can be monitored, but markers may migrate and become unreliable
Solution Approach 1:
The target structure's own material properties serve as the tracking reference, eliminating migration issues associated with implanted markers. Since the material properties are intrinsic to the target tissue itself, they remain stable and reliably represent the target's position throughout treatment.
Solution Approach 2:
The system transitions from tracking physical marker positions to tracking material property parameters (density, effective atomic number) of the target structure. This parameter-based approach provides continuous, stable reference data that doesn't suffer from physical displacement or migration.
3Measurement precision
If template matching based on material properties is implemented, then tracking accuracy improves, but computational complexity increases
Solution Approach 1:
The patent replaces traditional image intensity-based matching with material property-based matching using AI processing. The AI engine transforms raw image data into material property data (density, effective atomic number) that provides more robust tracking signals, substituting complex computational image analysis with physics-based material characterization.
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
Improves tracking accuracy and dose conformity by using material properties for template matching, reducing reliance on invasive markers and enhancing precision in radiation therapy.
Implementation Method 1
The image data may be treatment image data acquired during a treatment phase of the radiation therapy
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Example methods (100) and systems (300, 400) for image data processing for target structure tracking are described. In one example, a computer system may obtain treatment image data (140) associated with a target structure of a patient requiring radiation therapy. The treatment image data (140) may be acquired using an imaging system during a treatment phase (102) of the radiation therapy. The computer system may process (160) the treatment image data (140) using an artificial intelligence (Al) engine to generate material property data representing a particular material property associated with the target structure. The material property data may be generated to be matchable against a template that also represents the particular material property for tracking the target structure based on the particular material property during the treatment phase (102).