Robust catheter identification and tracking in X-ray angiographic sequences

Area of Science:

• Medical Imaging
• Biomedical Engineering
• Cardiovascular Diagnostics

Background:

• Coronary artery disease (CAD) is a leading global cause of mortality.
• X-ray angiography is the standard diagnostic tool for CAD, but image quality issues often hinder analysis.
• Catheter presence in angiography images complicates accurate vessel extraction due to structural similarities.

Purpose of the Study:

• To develop a fully automatic method for catheter detection and tracking in X-ray angiography sequences.
• To address image quality degradation issues affecting CAD diagnosis.
• To improve the reliability of vessel extraction in the presence of catheters.

Main Methods:

• Utilizing a vesselness map and guided filter for image smoothing.
• Employing Hough transform for initial catheter detection in the first frame.
• Fitting a second-order polynomial for accurate catheter tracking throughout the sequence.

Main Results:

• The proposed method successfully detects and tracks catheters in X-ray angiography sequences.
• Achieved a precision of 0.9597 on 25 tested sequences.
• Demonstrated robustness in handling image quality degradations.

Conclusions:

• The developed automatic catheter detection and tracking method is effective for X-ray angiography.
• This technique can significantly aid in improving the accuracy of vessel extraction for CAD diagnosis.
• The method offers a valuable tool for enhancing the clinical utility of cardiovascular imaging.