In vivo identification of uric acid stones with dual-energy CT: diagnostic performance evaluation in patients

To prospectively investigate the in vivo diagnostic performance of dual-energy (DE) computed tomography (CT) for the differentiation between uric acid (UA)-containing and non-UA-containing urinary stones. DE CT scans were performed in 180 patients with suspected urinary stone disease using a dual-source CT scanner in the DE mode (tube voltages 80 and 140 kV). Urinary stones were classified as UA-containing or non-UA-containing based on CT number measurements and DE software results. Sensitivity, specificity, positive predictive values (PPV), and negative predictive values (NPV) for the detection of UA-containing urinary stones were calculated using the crystallographic stone analysis as the reference standard. DE CT detected 110/180 patients (61%) with urinary stone disease. In 53 patients, stones were sampled. Forty-four out of 53 stones (83%) were non-UA-containing; and nine stones (17%) were UA-containing. The software automatically mapped 52/53 (98%) stones. One non-UA-containing stone (UA, 2 mm) was missed; one UA-containing stone (3 mm) was misclassified by software analysis. The sensitivity, specificity, PPV, and NPV for the detection of UA-containing stones was 89% (8/9, 95% CI: 52-100%), 98% (43/44, 95% CI: 88-100%), 89% (8/9, 95% CI: 52-100%), and 98% (43/44, 95% CI: 88-100%). Our results indicate that DE dual-source CT permits for the accurate in vivo differentiation between UA-containing and non-UA-containing urinary stones.