Accuracy and Time-Efficiency of an Automated Software Tool to Assess Left Ventricular Parameters in Cardiac Magnetic Resonance Imaging
Pablo Bartolomé (1), Meylin Caballeros (1), Almudena Quílez-Larragan (1), Jorge M Núñez-Córdoba (2, 3), Óscar Fernández González (4), Ana Ezponda (1), Gorka Bastarrika (1)
(1) Department of Radiology, Cardiothoracic Imaging Division, Clínica Universidad de Navarra.
(2) Research Support Service, Central Clinical Trials Unit, Clínica Universidad de Navarra.
(3) Department of Preventive Medicine and Public Health, School of Medicine, University of Navarra, Pamplona.
(4) Siemens Healthineers, Madrid, Spain
Purpose: Routine manual tracing of cardiac contours is time-consuming and subject to variability. A fully automated software tool may improve reading efficiency.
This study was performed to assess the accuracy, reliability, and time-efficiency of a fully automated left ventricular (LV) segmentation software tool to calculate LV volumes and function compared with conventional manual contouring.
Materials and methods: Sixty-seven consecutive patients (53 male, mean age 62.5±10.9 y) underwent adenosine stress/rest perfusion cardiac magnetic resonance examination to rule out myocardial ischemia.
Double-oblique short-axis 6-mm slice thickness steady-state free precession cine images were acquired to assess LV ejection fraction (EF), end-diastolic volume (EDV), end-systolic volume (ESV), and stroke volume (SV) using manual contour tracing and a recently developed fully automated software tool. The length of time needed to obtain LV volumes with each segmentation method was also compared.
Results: Compared with manual contouring, the fully automated software tool minimally underestimated LV-EF (mean difference of 2.9%±3.9%) and SV (mean difference of 4.4±8.5 mL) and slightly overestimated ESV (mean difference of -6.4±10.8 mL) and LV mass (mean difference of -14±20.4 g).
EDV quantification did not statistically differ. Reliability for EF (concordance correlation coefficient [CCC]=0.92, 95% confidence interval [CI], 0.88-0.95), EDV (CCC=0.98, 95% CI, 0.97-0.99), ESV (CCC=0.96, 95% CI, 0.94-0.97), SV (CCC=0.93, 95% CI, 0.89-0.95), and LV mass (CCC=0.84, 95% CI, 0.76-0.89) was very good. The evaluated software allowed to quantify LV parameters with a 79% reduction in the time required for manual contouring (414.7±91 s vs. 85±16.1 s, respectively, P<0.001).
Conclusion: Quantification of LV volumes using the evaluated fully automated segmentation software is accurate and time-efficient.
CITA DEL ARTÍCULO J Thorac Imaging. 2020 Jan;35(1):64-70. doi: 10.1097/RTI.0000000000000459