X-ray Image Position Alignment Using Device Area Masking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing X-ray diagnostic apparatuses face errors in position alignment during fluoroscopic imaging due to device movement, particularly when the device overlaps with bone edges or when the device appears in both mask and live images at non-corresponding positions, leading to artifacts in blood vessel and fluoroscopy roadmap images.
Innovation Solution
A medical image processing apparatus that specifies a device area candidate in the live X-ray image before position alignment, either by removing or reducing the contribution of this area, using techniques such as trained models, blood vessel image analysis, or threshold-based methods to improve alignment accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If auto pixel shift technique is used for position alignment, then position alignment can be performed automatically, but errors occur when device moves during fluoroscopic imaging
Solution Approach 1:
The patent applies preliminary action by identifying and removing the device area from the live image before performing position alignment. This prevents the moving device from interfering with the alignment calculation between the mask image and live image, thereby maintaining high alignment accuracy while preserving automatic operation.
Solution Approach 2:
The patent extracts the device area from the live image by detecting the device's position and removing or masking that region. This isolation of the interfering element (device) allows the position alignment to be performed only on the remaining anatomical structures, resolving the contradiction between automation and precision.
2Loss of information
If device area is included in position alignment, then complete image information is used, but alignment errors occur due to device movement
Solution Approach 1:
The patent segments the live image into device area and non-device area. By dividing the image in this way, it selectively excludes only the problematic device region from position alignment while preserving all other anatomical information, thus maintaining both information completeness and alignment precision.
Solution Approach 2:
The device area is extracted and removed from the live image before position alignment. This extraction ensures that only relevant anatomical structures contribute to the alignment calculation, preventing device-induced errors while retaining complete anatomical information for diagnostic purposes.
3Quantity of substance
If mask image contains device at non-corresponding position, then device information is captured, but interference causes alignment errors
Solution Approach 1:
The patent extracts and removes the device area from both mask and live images before performing position alignment. This ensures that device information is preserved for diagnostic purposes while preventing device-related interference from degrading alignment precision.
Solution Approach 2:
The patent applies local quality by treating the device area differently from the rest of the image. The device region is selectively removed or masked only during the position alignment process, while maintaining its presence in the original images for diagnostic use. This localized treatment resolves the conflict between capturing device information and ensuring accurate alignment.
Data Source
AI summary
According to one embodiment, a medical image processing apparatus includes processing circuitry. The processing circuitry specifies, before position alignment between a first X-ray image and a second X-ray image which is acquired with a device inserted, a device area candidate in the second X-ray image as a candidate of an area where the device appears. The processing circuitry performs the position alignment using first processing of removing the specified device area candidate or second processing of reducing a contribution of the specified device area candidate.