X-ray Fluoroscopy Device Using DRR Templates for Real-Time Site Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current X-ray fluoroscopy devices face challenges in accurately detecting specific sites, especially when the site's shape changes with breathing phases, leading to increased calculation costs and reduced real-time processing capabilities, and require time-consuming template creation before radiotherapy, which is painful for patients and reduces therapy throughput.
Innovation Solution
An X-ray fluoroscopy device that uses a combination of template matching and machine learning, employing DRR images created from CT data to detect the position of specific sites, allowing for real-time tracking and eliminating the need for pre-radiotherapy template creation, while also accounting for bone regions and breathing phases.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If template matching is performed using multiple templates to account for breathing phases, then detection accuracy is improved, but calculation cost increases and real-time processing becomes difficult
Solution Approach 1:
The system performs preliminary action by creating DRR images from CT data before radiotherapy to establish templates that account for breathing phases in advance. This allows the template matching process to use pre-prepared reference images rather than requiring real-time creation of multiple breathing phase templates, reducing calculation cost during actual treatment while maintaining detection accuracy.
Solution Approach 2:
The system applies parameter changes by transforming 3D CT data into 2D DRR images through virtual fluoroscopy projection. This parameter transformation allows the use of synthesized images that capture breathing phase variations without requiring actual fluoroscopic images for each phase, thereby reducing the number of templates needed and lowering calculation cost while preserving detection accuracy.
2Measurement precision
If multiple templates are created using fluoroscopy before radiotherapy to account for breathing phases, then detection accuracy is improved, but treatment time increases and throughput decreases
Solution Approach 1:
The system performs preliminary action by generating DRR images from CT data obtained during treatment planning, which already encompasses breathing phase information. This allows templates to be created before radiotherapy without requiring additional fluoroscopic imaging sessions, thus maintaining detection accuracy while eliminating the time loss associated with pre-radiotherapy fluoroscopy.
Solution Approach 2:
The system applies copying by creating virtual fluoroscopic images (DRR) from 3D CT data instead of using actual fluoroscopic images. These synthesized copies capture the anatomical structures and breathing phase variations without requiring real fluoroscopic exposure, thereby maintaining detection accuracy while eliminating the time-consuming fluoroscopy procedure.
3Productivity
If DRR images are used for template creation, then real-time tracking is enabled and throughput increases, but detection accuracy may be compromised without proper bone region handling
Solution Approach 1:
The system applies taking out by extracting and removing bone regions from DRR images before performing template matching. Since bone regions have high contrast and can interfere with accurate detection of soft tissue structures like tumors, this extraction eliminates the interfering elements while preserving the relevant anatomical structures, thereby maintaining detection accuracy while enabling real-time tracking throughput.
Solution Approach 2:
The system applies local quality by applying different processing treatments to different regions of the DRR image. Specifically, bone regions are removed or modified while other regions are preserved for template matching. This localized processing ensures that the interfering bone structures do not compromise detection accuracy while maintaining the ability to perform real-time tracking.
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
This approach improves detection accuracy, reduces calculation costs, and enables quick and accurate tracking of specific sites, ensuring precise radiation delivery even when the breathing phase differs from the treatment plan, thus enhancing the efficiency and effectiveness of radiotherapy.
Implementation Method 1
an X-ray tube (11a, 11b); an X-ray detector (21a, 21b) for detecting an X-ray radiated from the X-ray tube (11a, 11b)
Data Source
AI summary
A control unit 30 includes: an image storage unit 31 constituted by a first image storage unit 32 that stores multiple templates created on the basis of an image including a specific site of a subject and a second image storage unit 33 that stores multiple positive images created on the basis of an image including the specific site of the subject; a learning unit 34 that, on the basis of the multiple positive images, creates a discriminator by machine learning; a position selection unit 35 that, with use of multiple images obtained by collecting an image including the specific site of the subject at a predetermined frame rate, selects a region including the specific site by machine learning using the discriminator; and a position detection unit 36 that detects the position of the specific site by performing template matching using the multiple templates on the region including the specific site selected by the position selection unit 35.