Two-Stage DRR Reconstruction for Radiation Treatment Alignment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing methods for patient position alignment in radiation treatment are time-consuming due to the high calculation cost of creating DRR images and require frequent patient repositioning, especially when the photography range of X-ray fluoroscopic images is reduced, leading to difficulties in accurately aligning the patient's position with the DRR image.
Innovation Solution
A medical image processing device that includes a first and second image acquirer, a generator, and a calculator, which generates reconstructed images with enlarged ranges to facilitate accurate alignment by comparing fluoroscopic images with DRR images, reducing the need for frequent recalculations and improving alignment efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If DRR image is created by reproducing the photography range of X-ray fluoroscopic image, then calculation cost is reduced, but alignment accuracy deteriorates when photography range is reduced
Solution Approach 1:
The patent divides the DRR image generation into two segments: a first DRR image with enlarged photography range for initial position search, and a second DRR image with photography range matching the X-ray fluoroscopic image for final alignment. This segmentation allows the system to benefit from both large coverage for accuracy and appropriate range for calculation efficiency.
Solution Approach 2:
The patent performs preliminary action by first generating a first DRR image with enlarged photography range to obtain an initial position estimate, then using this estimate to guide the generation of the second DRR image with matched photography range. This preliminary step avoids the need to search the entire image space, reducing calculation cost while maintaining accuracy.
2Measurement precision
If DRR image with enlarged photography range is generated, then alignment accuracy is improved, but calculation cost increases
Solution Approach 1:
The patent segments the DRR image generation process into two stages: first generating a DRR image with enlarged photography range to establish initial alignment, then generating a second DRR image with photography range matched to the X-ray fluoroscopic image for refined alignment. This segmentation allows the system to achieve high accuracy without the full computational burden of always generating enlarged-range DRR images.
Solution Approach 2:
The patent uses preliminary action by first creating a DRR image with enlarged photography range to obtain an initial position estimate, which then guides the creation of the second DRR image with matched range. This preliminary step reduces the calculation cost of the final alignment by narrowing the search space.
3Measurement precision
If patient position is aligned frequently during radiation treatment, then treatment precision is improved, but treatment time increases
Solution Approach 1:
The patent performs preliminary action by automatically calculating patient position alignment before each radiation treatment session using the two-stage DRR image generation method. This preliminary alignment calculation, which would otherwise be time-consuming, is performed in advance to determine the required bed adjustment, thereby reducing the time needed during the actual treatment process while maintaining high precision.
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
The device enables faster and more accurate patient position alignment, even with reduced photography ranges, by using a two-step search process to determine the suitable position for radiation treatment, thus enhancing the precision and efficiency of radiation therapy.
Implementation Method 1
the reconstruction of the DRR image from the three-dimensional CT image is performed by applying a ray tracing method to the data of the CT image
Implementation Method 2
an X-ray fluoroscopic image of the inside of the patient's body photographed in a state in which the patient is laid on the bed
Data Source
AI summary
A medical image processing device of an embodiment includes first and second image acquirers, a generator, and a calculator. The first image acquirer acquires a first fluoroscopic image of a patient. The second image acquirer acquires a second fluoroscopic image according to radiation of the patient at a time point different from that of acquisition of the first image using a detector. The generator generates a reconstructed image by reproducing the second image from the first image virtually arranged in a three-dimensional space on the basis of a position of the detector in the three-dimensional space. The calculator obtains a suitable position on the first image in the three-dimensional space on the basis of a degree of similarity between the second image and the reconstructed image. The generator generates the reconstructed image for use in the calculator and has a range larger than a range corresponding to the second image.