Test-Retest Reliability of the Assessment of Fatty Liver Disease Using Low-Dose Computed Tomography in Cardiac Patients

Non-alcoholic fatty liver disease (NAFLD) is a common disorder that is associated with the risk of cardiovascular diseases. Therefore, its prevalence is high in patients with coronary artery disease. In myocardial perfusion imaging (MPI), low-dose computed tomography (CT) scans are used for attenuation correction in separate stress and rest studies. Here, the test-retest reliability of CT-based quantification of NAFLD was evaluated using these two CT scans. The study population consisted of 261 patients (156 men and 105 women, age 66 +/- 10 years). Quantification of liver fat content was based on the radiodensity of the liver in Hounsfield units as well as in relation to corresponding values of the spleen. NAFLD was observed in 47 subjects (18%). CT quantification has good test-retest reliability in assessing NAFLD, with concordance correlation coefficient (CCC) ranging from 0.512 to 0.923, intraclass correlation coefficient (ICC) ranging from 0.513 to 0.923, and coefficient of variation ranging from 3.1 to 7.0%. Regarding the liver to spleen ratio, CCC for non-NAFLD patients and NAFLD patients was 0.552 and 0.911, respectively. For non-NAFLD patients ICC was 0.553 and NAFLD patients it was 0.913. The coefficient of variation for non-NAFLD and NAFLD patients was 4.9% and 3.1%, respectively. Our results suggest that low-dose CT is a feasible and well repeatable method but amount of liver fat contributes to repeatability. In NAFLD patients CCC and ICC were high reflecting excellent reliability, whereas in non-NAFLD patients test-retest reliability was moderate. Assessment of liver fat content can be used as additional information in studies where a CT scan has been done for other medical reasons, such as for low-dose attenuation correction CT along with MPI.