Shared Vessel Masks for Movement-Resilient X-Ray Overlays
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing X-ray imaging methods for vascular interventions face challenges in accurately overlaying vessel masks on live images due to patient movements, such as breathing and organ movements, which reduce the accuracy of the overlay images.
Innovation Solution
Generate a shared vessel mask based on at least two X-ray images taken at different acquisition timeframes representing different contrast-agent filling states, and use this mask to create overlay images for each live image, compensating for object movements by using machine-learning models like CNNs and transformers for vessel extraction and registration.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If vessel masks are overlaid on live images during vascular intervention to enhance vascular structure visibility, then the visibility and guidance accuracy are improved, but patient movements (breathing, organ movements) cause overlay inaccuracies
Solution Approach 1:
The patent applies preliminary action by generating a shared vessel mask in advance from multiple X-ray images taken at different contrast-agent filling states. This pre-generated mask is then used for overlaying on subsequent live images, avoiding the need to continuously update masks during the procedure and thereby reducing movement-related inaccuracies.
Solution Approach 2:
The patent merges multiple X-ray images captured at different contrast-agent filling states to generate a single shared vessel mask. This combination of multiple images allows for more accurate vascular structure representation that is less susceptible to movement artifacts, improving overlay accuracy when applied to live images.
2Measurement precision
If multiple X-ray images are acquired at different contrast-agent filling states to improve vascular structure representation, then the completeness and accuracy of vascular depiction are improved, but the acquisition time and procedural duration increase
Solution Approach 1:
The patent performs the time-consuming task of acquiring multiple X-ray images at different contrast-agent filling states as a preliminary action before the actual vascular intervention. This allows the vascular structure to be accurately mapped in advance, and the shared vessel mask generated once, avoiding repeated acquisitions during the procedure and thereby reducing overall time loss.
Data Source
AI summary
In an X-ray imaging method, at least two X-ray images are obtained of a region to be depicted in an object, wherein the at least two X-ray images correspond to different acquisition timeframes and represent a vascular structure of the object in different contrast-agent filling states. A shared vessel mask, which represents the vascular structure, is generated based on the at least two X-ray images. At least two live images of the region to be depicted are obtained, which correspond to different second acquisition timeframes. For each image of the at least two live images, depending on the shared vessel mask, a corresponding overlay image for displaying on a display device is generated.