Optimal phase for coronary interpretations and correlation of ejection fraction using late-diastole and end-diastole imaging in cardiac computed tomography angiography: implications for prospective triggering

Abstract

A typical acquisition protocol for multi-row detector computed tomography (MDCT) angiography is to obtain all phases of the cardiac cycle, allowing calculation of ejection fraction (EF) simultaneously with plaque burden. New MDCT protocols scanner, designed to reduce radiation, use prospectively acquired ECG gated image acquisition to obtain images at certain specific phases of the cardiac cycle with least coronary artery motion. These protocols do not we allow acquisition of functional data which involves measurement of ejection fraction requiring end-systolic and end-diastolic phases. We aimed to quantitatively identify the cardiac cycle phase that produced the optimal images as well as aimed to evaluate, if obtaining only 35% (end-systole) and 75% (as a surrogate for end-diastole) would be similar to obtaining the full cardiac cycle and calculating end diastolic volumes (EDV) and EF from the 35th and 95th percentile images. 1,085 patients with no history of coronary artery disease were included; 10 images separated by 10% of R-R interval were retrospectively constructed. Images with motion in the mid portion of RCA were graded from 1 to 3; with '1' being no motion, '2' if 0 to <1 mm motion, and '3' if there is >1 mm motion and/or non-interpretable study. In a subgroup of 216 patients with EF > 50%, we measured left ventricular (LV) volumes in the 10 phases, and used those obtained during 25, 35, 75 and 95% phase to calculate the EF for each patient. The average heart rate (HR) for our patient group was 56.5 +/- 8.4 (range 33-140). The distribution of image quality at all heart rates was 958 (88.3%) in Grade 1, 113 (10.42%) in Grade 2 and 14 (1.29%) in Grade 3 images. The area under the curve for optimum image quality (Grade 1 or 2) in patients with HR > 60 bpm for phase 75% was 0.77 +/- 0.04 [95% CI: 0.61-0.87], while for similar heart rates the area under the curve for phases 75 + 65 + 55 + 45% combined was 0.92 +/- 0.02. LV volume at 75% phase was strongly correlated with EDV (LV volume at 95% phase) (r = 0.970, P < 0.001). There was also a strong correlation between LVEF (75_35) and LVEF (95_35) (r = 0.93, P < 0.001). Subsequently, we developed a formula to correct for the decrement in LVEF using 35-75% phase: LVEF (95_35) = 0.783 x LVEF (75_35) + 20.68; adjusted R(2) = 0.874, P < 0.001. Using 64 MDCT scanners, in order to acquire >90% interpretable studies, if HR < 60 bpm 75% phase of RR interval provides optimal images; while for HR > 60 analysis of images in 4 phases (75, 35, 45 and 55%) is needed. Our data demonstrates that LVEF can be predicted with reasonable accuracy by using data acquired in phases 35 and 75% of the R-R interval. Future prospective acquisition that obtains two phases (35 and 75%) will allow for motion free images of the coronary arteries and EF estimates in over 90% of patients.

Fig. 1

Grades 1, 2 and 3 of right coronary artery motion, respectively

Fig. 2

ROC curves for two models created to assess the ability of the R–R interval phases to predict interpretable CTA using 64 MDCT in patients with HR > 60 bpm

Fig. 3

Scatteplot of studentized residuals vs. standardized residuals for the regression model of LV volume 95 vs. 75% phase

Fig. 4

Scatterplot of studentized residuals vs. standardized predicted value for regression model of LVEF (95_35) vs. LVEF (75_35)

Fig. 5

Predicting EDV. Abridged plot of the linear regression model comparing left ventricular volume using 95% phase (y-axis) vs. 75% phase (x-axis)

Fig. 6

Predicting LVEF. Abridged plot of the linear regression model comparing LVEF 95_35 vs. LVEF 75_35