Non-contrast myocardial T1 global and regional reference values at 3 Tesla cardiac magnetic resonance in aortic stenosis

Automated inversion time selection for late gadolinium-enhanced cardiac magnetic resonance imaging

OBJECTIVES

To develop and share a deep learning method that can accurately identify optimal inversion time (TI) from multi-vendor, multi-institutional and multi-field strength inversion scout (TI scout) sequences for late gadolinium enhancement cardiac MRI.

MATERIALS AND METHODS

Retrospective multicentre study conducted on 1136 1.5-T and 3-T cardiac MRI examinations from four centres and three scanner vendors. Deep learning models, comprising a convolutional neural network (CNN) that provides input to a long short-term memory (LSTM) network, were trained on TI scout pixel data from centres 1 to 3 to identify optimal TI, using ground truth annotations by two readers. Accuracy within 50 ms, mean absolute error (MAE), Lin's concordance coefficient (LCCC) and reduced major axis regression (RMAR) were used to select the best model from validation results, and applied to holdout test data. Robustness of the best-performing model was also tested on imaging data from centre 4.

RESULTS

The best model (SE-ResNet18-LSTM) produced accuracy of 96.1%, MAE 22.9 ms and LCCC 0.47 compared to ground truth on the holdout test set and accuracy of 97.3%, MAE 15.2 ms and LCCC 0.64 when tested on unseen external (centre 4) data. Differences in vendor performance were observed, with greatest accuracy for the most commonly represented vendor in the training data.

CONCLUSION

A deep learning model was developed that can identify optimal inversion time from TI scout images on multi-vendor data with high accuracy, including on previously unseen external data. We make this model available to the scientific community for further assessment or development.

CLINICAL RELEVANCE STATEMENT

A robust automated inversion time selection tool for late gadolinium-enhanced imaging allows for reproducible and efficient cross-vendor inversion time selection.

KEY POINTS

• A model comprising convolutional and recurrent neural networks was developed to extract optimal TI from TI scout images. • Model accuracy within 50 ms of ground truth on multi-vendor holdout and external data of 96.1% and 97.3% respectively was achieved. • This model could improve workflow efficiency and standardise optimal TI selection for consistent LGE imaging.

Imaging Challenges in Patients with Severe Aortic Stenosis and Heart Failure: Did We Find a Way Out of the Labyrinth?

Aortic stenosis (AS) is the most frequent degenerative valvular disease in developed countries. Its incidence has been constantly rising due to population aging. The diagnosis of AS was considered straightforward for a very long time. High gradients and reduced aortic valve area were considered as "sine qua non" in diagnosis of AS until a growing body of evidence showed that patients with low gradients could also have severe AS with the same or even worse outcome. This completely changed the paradigm of AS diagnosis and involved large numbers of parameters that had never been used in the evaluation of AS severity. Low gradient AS patients may present with heart failure (HF) with preserved or reduced left ventricular ejection fraction (LVEF), associated with changes in cardiac output and flow across the aortic valve. These patients with low-flow low-gradient or paradoxical low-flow low-gradient AS are particularly challenging to diagnose, and cardiac output and flow across the aortic valve have become the most relevant parameters in evaluation of AS, besides gradients and aortic valve area. The introduction of other imaging modalities in the diagnosis of AS significantly improved our knowledge about cardiac mechanics, tissue characterization of myocardium, calcium and inflammation burden of the aortic valve, and their impact on severity, progression and prognosis of AS, not only in symptomatic but also in asymptomatic patients. However, a variety of novel parameters also brought uncertainty regarding the clinical relevance of these indices, as well as the necessity for their validation in everyday practice. The aim of this review is to summarize the prevalence of HF in patients with severe AS and elaborate on the diagnostic challenges and advantages of comprehensive multimodality cardiac imaging to identify the patients that may benefit from surgical or transcatheter aortic valve replacement, as well as parameters that may help during follow-up.