Pediatric cardiac MRI: automated left-ventricular volumes and function analysis and effects of manual adjustments

Cardiac MRI is an accurate and reproducible technique for the assessment of left ventricular volumes and function. The accuracy of automated segmentation and the effects of manual adjustments have not been determined in children.

To evaluate automated segmentation and the effects of manual adjustments for left ventricular parameter quantification in pediatric cardiac MR images.

Left ventricular parameters were evaluated in 45 children with suspected myocarditis (age 13.4 ± 3.5 years, range 4-17 years) who underwent cardiac MRI. Dedicated software was used to automatically segment and adjust the parameters. Results of end-diastolic volume, end-systolic volume, stroke volume, myocardial mass, and ejection fraction were documented before and after apex/base adjustment and after apex/base/myocardial contour adjustment.

The software successfully detected the left ventricle in 42 of 45 (93.3%) children; failures occurred in the smallest and youngest children. Of those 42 children, automatically segmented end-diastolic volume (EDV) was 151 ± 47 ml, and after apex/base adjustment it was 146 ± 45 ml, after apex/base/myocardial contour adjustment 146 ± 45 ml. The corresponding results for end-systolic volume (ESV) were 66 ± 32 ml, 63 ± 29 ml and 64 ± 28 ml; for stroke volume (SV) they were 85 ± 25 ml, 83 ± 23 ml and 83 ± 23 ml; for ejection fracture (EF) they were 57 ± 10%, 58 ± 9% and 58 ± 9%, and for myocardial mass (MM) they were 104 ± 31 g, 95 ± 31 g and 94 ± 30 g. Statistically significant differences were found when comparing the EDV/ESV/MM results, the EF results after apex/base adjustment and after apex/base/myocardial contour adjustment and the SV results (except for comparing the SVs after apex/base adjustment and after apex/base/myocardial contour adjustment).

Automated segmentation for the evaluation of left ventricular parameters in pediatric MR images proved to be feasible. Automated segmentation + apex/base adjustment provided clinically acceptable parameters for the majority of cases.