Two-Stage Image Registration for Radiation Therapy Target Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current image registration methods in image-guided radiation therapy face challenges in accurately and efficiently locating moving targets within the body during radiation treatment, requiring improved accuracy and computational efficiency for spatial transformation between treatment planning and treatment room reference frames.
Innovation Solution
A two-stage image registration method is employed, utilizing a volumetric imaging system and stereoscopic x-ray imaging to consecutively register treatment planning images, intrafraction images, and intrafraction x-ray images, with transformations including rigid and non-rigid alignments, and the generation of digitally reconstructed radiographs to enhance accuracy and reliability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If current image registration methods are used to locate moving targets during radiation treatment, then the process can be completed, but the accuracy of target localization deteriorates due to anatomical changes and motion
Solution Approach 1:
The patent divides the image registration process into two distinct stages: a first image registration performed before treatment to establish initial alignment, and a second image registration performed during treatment to account for motion and anatomical changes. This segmentation allows each stage to be optimized for its specific purpose, improving overall localization accuracy while maintaining reliability throughout the treatment process.
Solution Approach 2:
The patent performs preliminary image registration and establishes a treatment plan before the actual radiation treatment begins. This preliminary action creates a reference framework that can then be updated during treatment through the second registration stage, allowing the system to adapt to anatomical changes while maintaining the benefits of pre-planned treatment geometry.
2Measurement precision
If complex image registration methods are employed to improve accuracy, then target localization precision improves, but computational time and processing complexity increase
Solution Approach 1:
By dividing registration into two stages, the patent performs computationally intensive operations once during the first registration before treatment, and uses faster, more efficient algorithms during the second registration during treatment. This segmentation reduces the computational burden during time-critical treatment delivery while maintaining high accuracy through the combination of both stages.
Solution Approach 2:
The patent applies a pragmatic approach by performing full-precision registration once in advance (first registration) and then using optimized, faster registration methods during treatment (second registration). This partial application of full precision where most needed, combined with efficient approximation methods where sufficient, balances accuracy requirements with time constraints during radiation delivery.
Data Source
AI summary
A method of the present disclosure includes performing, by a processing device, a first image registration between a reference image of a patient and a motion image of the patient to perform alignment between the reference image and the motion image, wherein the reference image and the motion image include a target position of the patient. The method further includes performing, by the processing device, a second image registration between the reference image and a motion x-ray image of the patient, via a first digitally reconstructed radiograph (DRR) for the reference image of the patient. The method further includes tracking at least a translational change in the target position based on the first registration and the second registration.