Radiation Therapy ROI Localization Using Marker-Based Image Registration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional radiation therapy methods, such as boron neutron capture therapy, face challenges in accurately delineating regions of interest (ROIs) due to reliance on manual physician expertise, leading to inconsistent and time-consuming ROI definition, which affects treatment plan accuracy and increases normal tissue exposure risks.
Innovation Solution
A method and system for automatically and accurately defining ROIs using image data from different states with and without markers, employing multi-mode imaging devices to register and align images, and setting a marker parameter threshold for precise ROI delineation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual delineation of regions of interest is performed by physicians, then the process allows for expert judgment and flexibility, but it is time-consuming and lacks consistency and accuracy
Solution Approach 1:
The system enables automatic ROI delineation using image processing algorithms and marker parameter analysis, allowing the computer system to perform the delineation task independently without requiring manual physician intervention for each case, thereby reducing time loss while maintaining accuracy through automated threshold-based segmentation
Solution Approach 2:
The invention uses marker parameters (such as radiotracer uptake values) as quantitative thresholds to automatically define ROI boundaries, changing from subjective visual assessment to objective parameter-based segmentation, which improves both accuracy and consistency while reducing the time required for delineation
2Reliability
If manual delineation of regions of interest is performed by physicians, then expert judgment can be applied, but the results heavily depend on physician expertise and lack consistency
Solution Approach 1:
The system transforms subjective physician judgment into objective parameter-based decision making by using marker parameter thresholds (e.g., standardized uptake values) to automatically determine ROI boundaries, ensuring consistent and reproducible results across different cases and physicians while reducing system complexity through algorithmic standardization
3Reliability
If inaccurate ROI definition is used, then the treatment planning process is faster and simpler, but the assessment of irradiation dose becomes unreliable and normal tissue exposure increases
Solution Approach 1:
The invention replaces manual visual assessment with automated image processing and marker parameter analysis to define ROIs, using quantitative thresholds (such as SUV values) to objectively identify tumor boundaries and exclude normal tissues, thereby improving dose assessment reliability and reducing normal tissue exposure through precise automated segmentation
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
Enables quick and accurate ROI delineation, improving treatment plan reliability and reducing normal tissue exposure, thereby enhancing treatment efficacy and patient safety.
Implementation Method 1
acquiring first image data of an irradiated body in a first state or a second state; acquiring second image data of the irradiated body in the second state
Data Source
Figure 1
Figure 2~3
Figure 4~5(3)
AI summary
A method and a system for locating a region of interest in radiation therapy are provided. The method includes: acquiring first image data of an irradiated body in a first state or a second state; acquiring second image data of the irradiated body in the second state; registering and aligning the first image data with the second image data and acquiring a reference region based on the first image data or the second image data; obtaining a marker parameter based on the second image data, the marker parameter of the reference region being a reference value; and determining a set value based on a reference value and defining a region of interest based on the set value.