Non-invasive detection of exercise-induced cardiac conduction abnormalities in sudden cardiac death survivors in the inherited cardiac conditions.

AIMS: Rate adaptation of the action potential ensures spatial heterogeneities in conduction across the myocardium are minimized at different heart rates providing a protective mechanism against ventricular fibrillation (VF) and sudden cardiac death (SCD), which can be quantified by the ventricular conduction stability (V-CoS) test previously described. We tested the hypothesis that patients with a history of aborted SCD due to an underlying channelopathy or cardiomyopathy have a reduced capacity to maintain uniform activation following exercise. METHODS AND RESULTS: Sixty individuals, with (n = 28) and without (n = 32) previous aborted-SCD event underwent electro-cardiographic imaging recordings following exercise treadmill test. These included 25 Brugada syndrome, 13 hypertrophic cardiomyopathy, 12 idiopathic VF, and 10 healthy controls. Data were inputted into the V-CoS programme to calculate a V-CoS score that indicate the percentage of ventricle that showed no significant change in ventricular activation, with a lower score indicating the development of greater conduction heterogeneity. The SCD group, compared to those without, had a lower median (interquartile range) V-CoS score at peak exertion [92.8% (89.8-96.3%) vs. 97.3% (94.9-99.1%); P < 0.01] and 2 min into recovery [95.2% (91.1-97.2%) vs. 98.9% (96.9-99.5%); P < 0.01]. No significant difference was observable later into recovery at 5 or 10 min. Using the lowest median V-CoS scores obtained during the entire recovery period post-exertion, SCD survivors had a significantly lower score than those without for each of the different underlying aetiologies. CONCLUSION: Data from this pilot study demonstrate the potential use of this technique in risk stratification for the inherited cardiac conditions.

Automated analysis and detection of abnormalities in transaxial anatomical cardiovascular magnetic resonance images: a proof of concept study with potential to optimize image acquisition.

The large number of available MRI sequences means patients cannot realistically undergo them all, so the range of sequences to be acquired during a scan are protocolled based on clinical details. Adapting this to unexpected findings identified early on in the scan requires experience and vigilance. We investigated whether deep learning of the images acquired in the first few minutes of a scan could provide an automated early alert of abnormal features. Anatomy sequences from 375 CMR scans were used as a training set. From these, we annotated 1500 individual slices and used these to train a convolutional neural network to perform automatic segmentation of the cardiac chambers, great vessels and any pleural effusions. 200 scans were used as a testing set. The system then assembled a 3D model of the thorax from which it made clinical measurements to identify important abnormalities. The system was successful in segmenting the anatomy slices (Dice 0.910) and identified multiple features which may guide further image acquisition. Diagnostic accuracy was 90.5% and 85.5% for left and right ventricular dilatation, 85% for left ventricular hypertrophy and 94.4% for ascending aorta dilatation. The area under ROC curve for diagnosing pleural effusions was 0.91. We present proof-of-concept that a neural network can segment and derive accurate clinical measurements from a 3D model of the thorax made from transaxial anatomy images acquired in the first few minutes of a scan. This early information could lead to dynamic adaptive scanning protocols, and by focusing scanner time appropriately and prioritizing cases for supervision and early reporting, improve patient experience and efficiency.