Object Positioning Apparatus Using DRR Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In radiotherapy, the inclusion of unnecessary pixel regions such as the bed and medical restraints in X-ray images hinders accurate patient positioning due to obstacles in matching processing between radiographic and reference images.
Innovation Solution
An object positioning apparatus and method that removes unnecessary pixel regions from X-ray images before matching with Digitally Reconstructed Radiograph (DRR) images, using image processing techniques to enhance matching accuracy by specifying and eliminating non-index regions like the bed and medical restraints, allowing only the bone region to serve as an index for precise positioning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If pixel regions depicting unnecessary objects such as bed and medical restraint are removed from the DRR image, then the DRR image quality is improved, but the X-ray image still includes these unnecessary pixel regions which become obstacles to positioning
Solution Approach 1:
The patent extracts and removes pixel regions depicting unnecessary objects (bed, medical restraint) from the X-ray image before performing matching processing with the DRR image. This extraction process isolates the useful information (patient anatomy) from harmful distractions, enabling accurate positioning by comparing only relevant anatomical structures between the two images.
2Device complexity
If matching processing is performed between DRR image and X-ray image that both include unnecessary pixel regions, then processing is simpler, but matching accuracy deteriorates due to obstacles from unnecessary regions
Solution Approach 1:
The patent performs preliminary processing on the X-ray image by removing unnecessary pixel regions before the matching processing step. This preliminary action prepares the data in advance, ensuring that only relevant anatomical structures are present for comparison, thereby guaranteeing high matching accuracy without adding complexity to the subsequent processing steps.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An object positioning apparatus comprising: a radiographic image input interface configured to acquire a radiographic image that is generated by causing a fluoroscopic imaging apparatus to image an object and includes a first region and a second region, the first region depicting an index region for positioning of the object, the second region depicting a non-index region other than the index region; and a positioning processor configured to perform the positioning of the object by performing matching processing between a previously generated reference image and the first region that is specified from the radiographic image based on three-dimensional model information of the non-index region.