Cardiac magnetic resonance imaging: the future is bright.

Karthik Seetharam,Stamatios Lerakis

doi:10.12688/f1000research.19721.1

Karthik Seetharam, Stamatios Lerakis

Open Access

https://doi.org/10.12688/f1000research.19721.1

Copy DOI

Abstract

Over the last 15 years, cardiovascular magnetic resonance (CMR) imaging has progressively evolved to become an indispensable tool in cardiology. It is a non-invasive technique that enables objective and functional assessment of myocardial tissue. Recent innovations in magnetic resonance imaging scanner technology and parallel imaging techniques have facilitated the generation of T1 and T2 parametric mapping to explore tissue characteristics. The emergence of strain imaging has enabled cardiologists to evaluate cardiac function beyond conventional metrics. Significant progress in computer processing capabilities and cloud infrastructure has supported the growth of artificial intelligence in CMR imaging. In this review article, we describe recent advances in T1/T2 mapping, myocardial strain, and artificial intelligence in CMR imaging.

Highlights

Cardiovascular magnetic resonance (CMR) imaging has rapidly emerged as a robust diagnostic option for evaluating a number of pathological entities in cardiology
The authors showed that indexed extracellular volume measurement (ECV) was higher in patients with Low-flow low-gradient aortic stenosis (LFLG AS) with and without flow reserve (FR) in comparison with high-gradient AS (35.25 ± 9.75 versus 32.93 ± 11.00 versus 21.19 ± 6.47 mL/m2, respectively; P
Recent studies using strain in cardiovascular magnetic resonance Gatti et al explored the role of feature tracking (FT) strain in CMR for detecting subclinical systolic and diastolic dysfunction in 30 acute myocarditis patients with preserved ejection fraction[21]

Summary

Introduction

Cardiovascular magnetic resonance (CMR) imaging has rapidly emerged as a robust diagnostic option for evaluating a number of pathological entities in cardiology. Recent studies using strain in cardiovascular magnetic resonance Gatti et al explored the role of FT strain in CMR for detecting subclinical systolic and diastolic dysfunction in 30 acute myocarditis patients with preserved ejection fraction[21]. Image segmentation can be time-consuming and challenging in CMR This was applied to a number of datasets, which included the Hannover Medical School data science bowl cardiac challenge and the Medical Image Computing and Computer Assisted Intervention (MICCAI) 2009 left ventricular segmentation challenge. Tan et al explored the role of a convolutional network, a deep learning approach, for automatic segmentation of the left ventricle in all short-axis slices[33] This ML approach was applied to a number of publicly available datasets, which included the left ventricular segmentation challenge dataset containing 200 CMR imaging sets with diverse cardiac pathology. If newer software can successfully integrate clinical and imaging information, it can facilitate the expansion and utilization of ML in various academic centers

Conclusions

Findings

18. Ibrahim el-SH