High interstudy repeatability of automatic deep learnt biventricular CMR measurements

Abstract

Abstract Funding Acknowledgements Type of funding sources: Foundation. Main funding source(s): Wellcome Trust (UK), NIHR (UK) Introduction Cardiac magnetic resonance (CMR) measurements have significant diagnostic and prognostic value. Accurate and repeatable measurements are essential to assess disease severity, evaluate therapy response and monitor disease progression. Deep learning approaches have shown promise for automatic left ventricular (LV) segmentation on CMR, however fully automatic right ventricular (RV) segmentation remains challenging. We aimed to develop a biventricular automatic contouring model and evaluate the interstudy repeatability of the model in a prospectively recruited cohort. Methods A deep learning CMR contouring model was developed in a retrospective multi-vendor (Siemens and General Electric), multi-pathology cohort of patients, predominantly with heart failure, pulmonary hypertension and lung diseases (n = 400, ASPIRE registry). Biventricular segmentations were made on all CMR studies across cardiac phases. To test the accuracy of the automatic segmentation, 30 ASPIRE CMRs were segmented independently by two CMR experts. Each segmentation was compared to the automatic contouring with agreement assessed using the Dice similarity coefficient (DSC). A prospective validation cohort of 46 subjects (10 healthy volunteers and 36 patients with pulmonary hypertension) were recruited to assess interstudy agreement of automatic and manual CMR assessments. Two CMR studies were performed during separate sessions on the same day. Interstudy repeatability was assessed using intraclass correlation coefficient (ICC) and Bland-Altman plots. Results DSC showed high agreement (figure 1) comparing automatic and expert CMR readers, with minimal bias towards either CMR expert. The scan-scan repeatability CMR measurements were higher for all automatic RV measurements (ICC 0.89 to 0.98) compared to manual RV measurements (0.78 to 0.98). LV automatic and manual measurements were similarly repeatable (figure 2). Bland-Altman plots showed strong agreement with small mean differences between the scan-scan measurements (figure 2). Conclusion Fully automatic biventricular short-axis segmentations are comparable with expert manual segmentations, and have shown excellent interstudy repeatability.