Polarization-sensitive optical coherence tomography-based fully-automated volumetric coronary fibrous cap...

Area of Science:

• Cardiovascular Imaging
• Biomedical Engineering
• Computational Pathology

Background:

• Accurate characterization of coronary fibrous caps is crucial for estimating plaque rupture risk.
• Current intravascular imaging techniques have limitations in contrast and manual interpretation, hindering volumetric cap morphology assessments.

Purpose of the Study:

• To present CapSeg, a fully automated computational pipeline for in vivo fibrous cap segmentation and thickness measurement using intravascular polarization-sensitive OCT (IV-PS-OCT).
• To enable automated extraction of minimum cap thickness and polarization properties across entire vessel segments by differentiating fibrous caps from lipid-rich cores.

Main Methods:

• Developed CapSeg, a computational pipeline leveraging reflectance, birefringence, and depolarization metrics from IV-PS-OCT.
• Validated CapSeg's minimum cap thickness measurements against manual annotations from two expert observers using 200 cross-sectional coronary IV-PS-OCT images.
• Applied the pipeline to volumetric IV-PS-OCT data of 38 coronary lesions in patients with acute or chronic coronary syndrome.

Main Results:

• Automated cap thickness measurements by CapSeg showed strong agreement with manual assessments, comparable to inter-observer variability.
• Analysis of coronary lesions revealed decreased birefringence and increased depolarization in fibrous caps of patients with acute coronary syndrome compared to chronic coronary syndrome.

Conclusions:

• CapSeg provides fast, reproducible, and fully automated fibrous cap evaluation.
• The pipeline facilitates large-scale clinical studies and real-time intravascular imaging applications for improved cardiovascular risk assessment.