Automatic X-Ray Collimation for Workflow-Guided Radiation Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing X-ray monitoring systems in complex medical interventions, such as minimally invasive procedures, fail to effectively reduce radiation exposure due to inadequate collimation of the irradiated field of view, leading to operator distraction and increased radiation exposure for both patients and medical staff.
Innovation Solution
An X-ray device with automatic actuation capabilities that segments and classifies objects in real-time using machine-learning algorithms, adjusts the collimator to focus on relevant objects or sections, and acquires X-ray images with minimized background exposure, allowing operators to concentrate on the intervention without manual collimation adjustments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If manual collimation is performed by operator, then collimation can be adjusted based on current situation, but it is time-consuming and leads to interruption of clinical workflow
Solution Approach 1:
The system performs automatic collimation by itself without requiring operator intervention. The control unit automatically determines the region of interest from the X-ray image and adjusts the collimator accordingly, allowing the system to serve itself in the collimation task and eliminating workflow interruptions.
Solution Approach 2:
The manual mechanical operation of adjusting collimator diaphragms by the operator is replaced by an automated control system that uses image processing algorithms to determine the region of interest and automatically positions the collimator, substituting mechanical manual adjustment with automated electronic control.
2Adaptability or versatility
If manual collimation is performed by operator, then collimation can be adjusted based on current situation, but the procedure is non-reproducible and dependent on particular operator
Solution Approach 1:
The subjective human judgment and manual mechanical adjustment are replaced by an automated control system that applies consistent image processing algorithms to determine the region of interest, ensuring reproducible and objective collimation decisions independent of which operator performs the procedure.
Solution Approach 2:
The system continuously monitors the X-ray image quality and automatically adjusts the collimation based on feedback from image analysis. The control unit processes the current X-ray image, identifies the region of interest, and adjusts the collimator settings accordingly, creating a closed-loop feedback system that ensures consistent and reproducible collimation.
3Extent of automation
If automatic collimation is performed based on registered volumes or detected objects, then collimation can be automated, but the collimation is not specific enough to significantly reduce radiation exposure when objects fill most of the image
Solution Approach 1:
Instead of applying uniform collimation across the entire field of view or based on simple object detection, the system applies localized collimation by precisely identifying the specific region of interest within the image. The control unit determines the boundaries of the region of interest and adjusts the collimator to overlay only that specific area, maintaining automation while achieving specific and effective radiation reduction.
4Ease of operation
If manual collimation is performed, then operator can control the overlay region, but operator has to deal with controlling the collimator which causes distraction and slows down the intervention
Solution Approach 1:
The control of the collimator is transferred from the operator to the automated system. The control unit independently determines the region of interest and adjusts the collimator without requiring operator attention or action, allowing the operator to focus entirely on the medical intervention and improving overall productivity.
Data Source
AI summary
A method for automatic actuation of an X-ray device includes acquiring at least one X-ray image of a body containing at least two objects and/or an object divisible into at least two object sections, segmenting and classify the at least two objects and/or the at least two object sections of the object, and determining an immediately upcoming or current workflow step of the intervention. Information relating to objects or object sections relevant to the determined workflow step is retrieved, at least one object of the at least two objects or at least one object section of the at least two object sections of the object is selected taking the information into account, and a collimator of the X-ray device is automatically adjusted for overlaying the selected object or selected object section taking the information into account. At least one X-ray image is acquired using the thus adjusted collimator and displayed.