Radiation Therapy DRR Generation Using Segmented Projection Synthesis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current radiation therapy alignment methods are inefficient due to the high computational complexity of generating digitally reconstructed radiographs (DRRs), which hinders high-speed and high-precision alignment of radiation beams with diseased areas, leading to prolonged processing times.
Innovation Solution
The implementation of a radiation therapy device that includes an acquirer, a projection position calculator, an element projection image generator, and an element projection image synthesizer, which generates and synthesizes element projection images to produce DRRs, reducing the computational burden and accelerating the alignment process by projecting three-dimensional images onto two-dimensional fluoroscopic images.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a ray tracing method is used for DRR generation, then the accuracy of the reconstructed image is improved, but the processing time is significantly increased
Solution Approach 1:
The patent segments the DRR generation process into multiple coarse-to-fine stages. Initially, a low-resolution DRR is generated using a simplified method, then progressively refined at higher resolutions. This segmentation allows the computationally intensive ray tracing to be applied only at necessary resolution levels, reducing overall processing time while maintaining final image accuracy.
Solution Approach 2:
The patent performs preliminary actions by generating a low-resolution DRR first using a computationally efficient method. This preliminary DRR is then used to determine alignment parameters, which are subsequently applied to generate a high-resolution DRR. This preliminary action avoids performing full high-resolution ray tracing from scratch, significantly reducing processing time while preserving accuracy.
2Measurement precision
If the number of DRR generation iterations is increased to improve alignment precision, then the alignment accuracy is improved, but the total processing time is significantly increased
Solution Approach 1:
The alignment process is segmented into multiple iterations with decreasing step sizes. Coarse alignment is performed first with larger adjustment steps, followed by fine alignment with smaller steps. This segmentation allows the system to converge to high precision without requiring an excessive number of full-resolution DRR generations, as each iteration builds upon the previous alignment result.
Solution Approach 2:
The patent implements dynamic adjustment of the DRR generation parameters during the alignment process. The resolution and calculation intensity are adapted based on the current alignment accuracy and remaining adjustment needs. This dynamic approach allows the system to spend more computational resources when precision is most needed and reduce resources when alignment is already satisfactory, optimizing the balance between accuracy and processing time.
Data Source
AI summary
According to an embodiment, a radiation therapy device includes an acquirer, a projection position calculator, an element projection image generator, and an element projection image synthesizer. The acquirer acquires a condition of X-ray imaging in a treatment stage and a three-dimensional image of a patient imaged before the treatment stage. The projection position calculator calculates a projection position when each of pixels included in the three-dimensional image is projected onto a two-dimensional X-ray fluoroscopic image generated in the X-ray imaging on the basis of the condition of the X-ray imaging. The element projection image generator generates an element projection image for each pixel when each of the pixels included in the three-dimensional image is projected onto the X-ray fluoroscopic image. The element projection image synthesizer performs a synthesis process for the element projection image for each pixel on the basis of the projection position to generate a reconstructed image.