Intracoronary Optical Coherence Tomography Image Processing and Vessel Classification Using Machine Learning

TL;DR

This paper presents an automated machine learning pipeline for high-accuracy vessel segmentation and classification in intracoronary OCT images, addressing noise and artifacts for clinical use.

Contribution

It introduces a comprehensive, fully automated OCT image processing method combining preprocessing, artifact removal, feature extraction, and machine learning classifiers, with high accuracy and low manual effort.

Findings

Achieved 99.68% overall classification accuracy.

Demonstrated high precision, recall, and F1-score up to 1.00.

Provided a computationally efficient solution for clinical OCT analysis.

Abstract

Intracoronary Optical Coherence Tomography (OCT) enables high-resolution visualization of coronary vessel anatomy but presents challenges due to noise, imaging artifacts, and complex tissue structures. This paper proposes a fully automated pipeline for vessel segmentation and classification in OCT images using machine learning techniques. The proposed method integrates image preprocessing, guidewire artifact removal, polar-to-Cartesian transformation, unsupervised K-means clustering, and local feature extraction. These features are used to train Logistic Regression and Support Vector Machine classifiers for pixel-wise vessel classification. Experimental results demonstrate excellent performance, achieving precision, recall, and F1-score values up to 1.00 and overall classification accuracy of 99.68%. The proposed approach provides accurate vessel boundary detection while maintaining low computational complexity and requiring minimal manual annotation. This method offers a reliable and efficient solution for automated OCT image analysis and has potential applications in clinical decision support and real-time medical image processing.