Vascular Catheter Tip Detection Using Cropped X-Ray Image Sequences
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The detection of the tip of a vascular catheter in medical images is challenging due to occlusion by contrast medium, low signal-to-noise ratio, interference from radio-opaque anatomical landmarks, and non-anatomical landmarks such as other catheters or pacemakers, making accurate tracking difficult.
Innovation Solution
A method involving determining a proximal point, cropping the image frames to surround this point, detecting the catheter tip in frames without contrast medium, and tracking its position across frames using image segmentation and correlation techniques.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the entire image area is analyzed for catheter tip detection, then comprehensive detection coverage is achieved, but detection accuracy deteriorates due to interference from contrast medium, radio-opaque landmarks, and low signal-to-noise ratio
Solution Approach 1:
The patent segments the image analysis process into distinct phases: first identifying the proximal point (vessel ostium) in contrast-enhanced frames, then using that location to define a restricted region of interest for subsequent tip detection in non-contrast frames. This segmentation isolates the detection process from interfering elements in other image regions.
Solution Approach 2:
The patent extracts and removes interfering elements from the detection process by selectively using non-contrast-enhanced frames for tip detection after establishing the search region. This extraction eliminates contrast medium interference and radio-opaque landmark interference from the critical detection phase while preserving necessary anatomical context.
2Measurement precision
If contrast medium is used to enhance vessel visibility, then vessel landmarks become more detectable, but catheter tip detection is obscured by the radio-opaque contrast medium
Solution Approach 1:
The patent performs preliminary detection of the proximal point using contrast-enhanced frames before proceeding to tip detection. By completing the anatomical landmark identification and region definition in advance, the system establishes a controlled search area that eliminates contrast medium interference during the actual tip detection phase.
Solution Approach 2:
The patent employs periodic action by alternating between contrast-enhanced frames (for proximal point detection) and non-contrast-enhanced frames (for tip detection). This temporal separation allows each detection task to be performed under optimal conditions without mutual interference.
3Reliability
If image processing is performed on the full image sequence, then all potential catheter positions are considered, but processing time and computational complexity increase significantly
Solution Approach 1:
The patent applies local quality by concentrating computational resources on a restricted region of interest defined by the proximal point location. Instead of analyzing the entire image sequence uniformly, the system focuses processing power on a localized area where the catheter tip is most likely to be found, maintaining detection reliability while reducing overall processing time.
Data Source
Figure 1
Figure 2~4
Figure 5
AI summary
The present disclosure relates to a method for detecting a tip of a vascular catheter in a sequence of vessel image frames obtained using x-rays. The method comprises the steps of determining, within the vessel image frames, a proximal point, the proximal point corresponding to a vessel ostium, cropping the sequence of vessel image frames to an image area surrounding the proximal point to generate a cropped sequence of cropped vessel image frames, detecting, within cropped vessel image frames not indicative of a contrast medium, the tip of the vascular catheter, and tracking, within the sequence of vessel image frames, the detected tip of the vascular catheter.