Search

Objectives: The aim of this study is to develop a scar detection method for routine computed tomography angiography (CTA) imaging using deep convolutional neural networks (CNN), which relies solely on anatomical information as input and is compatible with existing clinical workflows.Background: Identifying cardiac patients with scar tissue is important for assisting diagnosis and guiding interventions. Late gadolinium enhancement (LGE) magnetic resonance imaging (MRI) is the gold standard for scar imaging; however, there are common instances where it is contraindicated. CTA is an alternative imaging modality that has fewer contraindications and is faster than Cardiovascular magnetic resonance imaging but is unable to reliably image scar.Methods: A dataset of LGE MRI (200 patients, 83 with scar) was used to train and validate a CNN to detect ischemic scar slices using segmentation masks as input to the network. MRIs were segmented to produce 3D left ventricle meshes, which were sampled at points along the short axis to extract anatomical masks, with scar labels from LGE as ground truth. The trained CNN was tested with an independent CTA dataset (25 patients, with ground truth established with paired LGE MRI). Automated segmentation was performed to provide the same input format of anatomical masks for the network. The CNN was compared against manual reading of the CTA dataset by 3 experts.Results: Note that 84.7% cross-validated accuracy (AUC: 0.896) for detecting scar slices in the left ventricle on the MRI data was achieved. The trained network was tested against the CTA-derived data, with no further training, where it achieved an 88.3% accuracy (AUC: 0.901). The automated pipeline outperformed the manual reading by clinicians.Conclusion: Automatic ischemic scar detection can be performed from a routine cardiac CTA, without any scar-specific imaging or contrast agents. This requires only a single acquisition in the cardiac cycle. In a clinical setting, with near zero additional cost, scar presence could be detected to triage images, reduce reading times, and guide clinical decision-making.

Oscillations of arterial pressure occur spontaneously at a frequency of approx. 0.1Hz coupled with synchronous oscillations of sympathetic nerve activity (Mayer waves). This study investigated the extent to which corresponding oscillations may occur in ventricular action potential duration (APD).14 ambulatory (outpatient) heart failure patients with biventricular pacing devices were studied while seated upright watching movie clips to maintain arousal. Activation recovery intervals (ARI) as a measure of ventricular APD were obtained from unipolar electrograms recorded from the LV epicardial pacing lead during steady state RV pacing from the device. Arterial blood pressure was measured non-invasively (Finapress) and respiration monitored. Oscillations were quantified using time frequency and coherence analysis.Oscillatory behaviour of ARI at the respiratory frequency was observed in all subjects. The magnitude of the ARI variation ranged from 2.2 ms to 6.9 ms (mean 5.0 ms). Coherence analysis showed a correlation with respiratory oscillation for an average of 43% of the recording time at a significance level of p < 0.05. Oscillations in systolic blood pressure in the Mayer wave frequency range were observed in all subjects for whom blood pressure was recorded (n=13). ARI oscillation in the Mayer wave frequency range was observed in 6/13 subjects (46%) over a range of 2.9ms to 9.2ms. Coherence with Mayer waves at the p < 0.05 significance level was present for an average of 29 % of the recording time. In ambulatory patients with heart failure during enhanced mental arousal, left ventricular epicardial APD (ARI) oscillated at the respiratory frequency (approx. 0.25Hz). In 6 patients (46%) APD oscillated at the slower Mayer wave frequency (approx. 0.1 Hz). These findings may be important in understanding sympathetic activity-related arrhythmogenesis.