A review on machine learning for arterial extraction and quantitative assessment on invasive coronary angiograms

TL;DR

This review summarizes recent advancements in machine learning techniques applied to invasive coronary angiography for artery segmentation and quantitative assessment, highlighting progress and ongoing challenges in clinical integration.

Contribution

It provides a comprehensive overview of machine learning applications in ICA for coronary segmentation and assessment, emphasizing current methods and future needs.

Findings

Machine learning improves coronary artery segmentation accuracy.

ML techniques enhance quantitative evaluation like FFR and stenosis assessment.

Challenges remain for clinical integration of ML algorithms.

Abstract

Purpose of Review Recently, machine learning has developed rapidly in the field of medicine, playing an important role in disease diagnosis. Our aim of this paper is to provide an overview of the advancements in machine learning techniques applied to invasive coronary angiography (ICA) for segmentation of coronary arteries and quantitative evaluation like fractional flow reserve (FFR) and stenosis assessment. Recent Findings ICA are used extensively along with machine learning techniques for the segmentation of arteries and quantitative evaluation of stenosis, coronary artery disease and measurement of fractional flow reserve, representing a trend towards using computational methods for enhanced diagnostic precision in cardiovascular medicine. Summary Various research studies have been conducted in this field, each using different algorithms and datasets. The performance of these studies largely depends on the algorithms employed and the datasets used for training and evaluation. However, despite the progress made, there remains a need for machine learning (ML) algorithms that can be easily integrated into clinical practice.