Quantification of nonculprit coronary lesions: comparison of cardiac 64-MDCT and invasive coronary angiography

Abstract

Objective: The purpose of our study was to evaluate the accuracy of cardiac 64-MDCT to quantify the grade of stenosis of nonculprit lesions.

Subjects and methods: Twenty-nine consecutive patients (23 men and six women; mean age, 62 +/- 10 years) presenting with acute coronary syndrome (ACS) had nonculprit coronary lesions of >or= 30% stenosis quantified on quantitative coronary angiography (QCA). Five 64-MDCT postprocessing techniques (maximum intensity projection [MIP], multiplanar reformat [MPR], cross-sectional area [CSA], and diameter and area derived from semiquantitative coronary software) were used to grade lesions. Two separate groups of two independent readers analyzed QCA and cardiac CT images using a 17-segment model. Coronary angiography was the reference standard.

Results: Nonculprit lesions were identified in 46 analyzable coronary segments. Subgrouping lesions on the basis of reference vessel diameter resulted in strong correlations for quantifying nonculprit lesions in vessels > 3 mm (R = 0.78-0.91, p < 0.01) but poor correlations for nonculprit lesions in vessels <or= 3 mm (R = 0.1-0.07). Subgrouping lesions on the basis of plaque type resulted in poor correlations for calcified plaques (R = 0.01-0.30) but moderate to strong correlations for mixed (R = 0.58-0.75, p < 0.01) and noncalcified (R = 0.44-0.61, p < 0.01) plaques. The best overall correlation among all CT techniques with QCA was CSA (R = 0.56, p < 0.01). Interobserver agreement (kappa values) for MPR, MIP, coronary software diameter and area were 0.6, 0.7, 0.62, and 0.57, respectively.

Conclusion: In patients presenting with ACS, 64-MDCT provided an accurate grade of stenosis for nonculprit coronary lesions in proximal coronary segments. Calcified plaques and lesions in coronary segments <or= 3 mm diameter remained difficult to accurately quantify.