Automatic Image Co-registration of Carotid Angiography and Intravascular Optical Coherence Tomography Based on...

Area of Science:

• Medical Imaging
• Biomedical Engineering
• Cardiovascular Diagnostics

Background:

• Carotid artery disease diagnosis relies on accurate imaging.
• Co-registration of different imaging modalities like OCT and angiography is crucial for comprehensive assessment.
• Existing methods may lack precision in aligning these diverse image types.

Purpose of the Study:

• To introduce a novel algorithm framework for optical coherence tomography (OCT) and carotid angiography co-registration (cACR).
• To enhance diagnostic precision and treatment planning for carotid artery disease.
• To achieve accurate and reliable alignment between OCT and angiography data.

Main Methods:

• Developed an OCT-cACR algorithm integrating an enhanced U-Net segmentation model and a marker detection algorithm.
• Utilized the You Only Look Once (YOLO) algorithm for OCT probe marker detection and tracking.
• Employed acquisition time points for modality matching and assessed geographical error using expert comparison.

Main Results:

• The segmentation model achieved superior accuracy (Dice coefficient: 0.867 ± 0.166) over baseline U-Net models.
• OCT-cACR demonstrated high accuracy (93.33% to 100%) in aligning angiography and OCT images across four clinical cases.
• The geographical error was maintained below the 0.35 mm evaluation criterion.

Conclusions:

• The proposed carotid angiography co-registration (cACR) approach is feasible and accurate.
• This novel algorithm serves as a promising tool for improving the diagnosis and treatment of carotid artery diseases.
• Precise image alignment facilitates better clinical decision-making in cardiovascular care.