An imaging technology developed using artificial intelligence (AI) could become an alternative for late gadolinium enhancement (LGE) cardiovascular magnetic resonance imaging (CMR) for non-invasive myocardial tissue characterisation, according to the findings of a study published in the journal Circulation.
The study by researchers from the University of Oxford assessed the use of a CMR virtual native enhancement (VNE) imaging technology, a deep-learning driven technology that generates images closely resembling conventional LGE without the need for a contrast agent. This may allow significantly faster, lower-cost and contrast-free CMR scans, enabling frequent monitoring of myocardial tissue changes, the study’s authors suggest.
Qiang Zhang, Stefan Piechnik, Vanessa Ferreira and colleagues used datasets from 1,348 hypertrophic cardiomyopathy (HCM) patients taken from the multicentre Hypertrophic Cardiomyopathy Registry (HCMR) to develop and test the technique. This included comparing, intra- and inter-observer agreement and lesion quantification.
Detailing their assessment of the technology in Circulation, Zhang et al note write that VNE had significantly better image quality than LGE, as assessed by four operators (n=345 datasets, p<0.001, Wilcoxon test), while VNE revealed characteristic HCM lesions in high visuospatial agreement with LGE. They add that in 121 patients (n=326 datasets), VNE correlated with LGE in detecting and quantifying both hyper-intensity myocardial lesions (r=0.77‒0.79, ICC=0.77‒0.87; p<0.001) and intermediate-intensity lesions (r=0.70‒0.76, ICC=0.82‒0.85; p<0.001). The authors note that while currently validated in HCM, there is a “clear pathway” to extend VNE to characterise a wider range of cardiac pathologies.
Commenting on the study, Zhang said: “We are excited by our new concept where AI could work as a ‘virtual’ contrast agent to replace the injections currently required when someone has a heart MRI scan. Our focus is to develop deep learning solutions for immediate patient benefit, and this AI tool could help to make heart MRI more accessible to patients and hospitals in the coming years.”