Feasibility of Ultrasound Attenuation Imaging for Assessing Pediatric Hepatic Steatosis

Abstract

We investigated the feasibility of ultrasound attenuation imaging (ATI) for assessing pediatric hepatic steatosis. A total of 111 children and adolescents who underwent liver ultrasonography with ATI for suspected hepatic steatosis were included. Participants were classified into the normal, mild, or moderate−severe fatty liver group according to grayscale US findings. Associations between clinical factors, magnetic resonance imaging proton density fat fraction, steatosis stage and ATI values were evaluated. To determine the cutoff values of ATI for staging hepatic steatosis, areas under the curve (AUCs) were analyzed. Factors that could cause measurement failure with ATI were assessed. Of 111 participants, 88 had successful measurement results. Median ATI values were significantly increased according to steatosis stage (p < 0.001). Body mass index (BMI) was a significant factor for increased ATI values (p = 0.047). To differentiate fatty liver from normal liver, a cutoff value of 0.59 dB/cm/MHz could be used with an AUC value of 0.853. To differentiate moderate to severe fatty liver from mild fatty liver, a cutoff value of 0.69 dB/cm/MHz could be used with an AUC value up to 0.91. ATI can be used in children as an effective ultrasonography technique for quantifying and staging pediatric hepatic steatosis.

Keywords: attenuation imaging; children; fat quantification; liver steatosis; ultrasonography.

Figure 1

A 7-year-old girl in the mild fatty liver group according to grayscale US. (a) The ATI value was 0.65 dB/cm/MHz and (b) MRI-PDFF value was 8.9% (S1: PDFF > 6%). US: ultrasonography; ATI: attenuation imaging; MRI: magnetic resonance imaging; PDFF: proton density fat fraction.

Figure 2

An 11-year-old girl in the moderate to severe fatty liver group according to grayscale US. (a) The ATI value was 0.83 dB/cm/MHz and (b) MRI-PDFF value was 30.7% (S3: PDFF > 23.3%). US: ultrasonography; ATI: attenuation imaging; MRI: magnetic resonance imaging; PDFF: proton density fat fraction.

Figure 3

Box–whisker plots of median ATI values for each hepatic steatosis group (a) according to US echogenicity and (b) MRI-PDFF value. US: ultrasonography; ATI: attenuation imaging; MRI: magnetic resonance imaging; PDFF: proton density fat fraction.

Figure 4

ROC curves of median ATI values for staging hepatic steatosis according to the grayscale US and MRI-PDFF. (a) For differentiating fatty liver (mild, moderate, severe) from the normal group according to the US criteria, a cutoff value of 0.59 dB/cm/MHz showed an AUC value of 0.853 (95% CI 0.762–0.920). (b) For differentiating moderate to severe fatty liver from mild fatty liver according to the US criteria, a cutoff value of 0.69 dB/cm/MHz showed an AUC value of 0.778 (95% CI 0.649–0.878). (c) For differentiating moderate to severe fatty liver from mild fatty liver according to MRI-PDFF, a cutoff value of 0.69 dB/cm/MHz showed an AUC value of 0.909 (95% CI 0.695–0.990). US: ultrasonography; ATI: attenuation imaging; MRI: magnetic resonance imaging; PDFF: proton density fat fraction; AUC: area under the curve; CI: confidence interval.

Figure 4

ROC curves of median ATI values for staging hepatic steatosis according to the grayscale US and MRI-PDFF. (a) For differentiating fatty liver (mild, moderate, severe) from the normal group according to the US criteria, a cutoff value of 0.59 dB/cm/MHz showed an AUC value of 0.853 (95% CI 0.762–0.920). (b) For differentiating moderate to severe fatty liver from mild fatty liver according to the US criteria, a cutoff value of 0.69 dB/cm/MHz showed an AUC value of 0.778 (95% CI 0.649–0.878). (c) For differentiating moderate to severe fatty liver from mild fatty liver according to MRI-PDFF, a cutoff value of 0.69 dB/cm/MHz showed an AUC value of 0.909 (95% CI 0.695–0.990). US: ultrasonography; ATI: attenuation imaging; MRI: magnetic resonance imaging; PDFF: proton density fat fraction; AUC: area under the curve; CI: confidence interval.