Automated deep learning detection of hepatic steatosis on non-contrast CT scans and discrepancy with scan reports.

BACKGROUND AND AIMS: Metabolic dysfunction-associated steatotic liver disease (MASLD) is a major cause of liver disease that is growing in prevalence. Typically asymptomatic, MASLD is often undiagnosed. Imaging studies, including non-contrast CT (NCCT) scans, can detect hepatic steatosis opportunistically, but the reporting rate is unknown. We hypothesized that incidental finding of steatosis on NCCT is often not reported if not specifically sought in the imaging request. METHODS: A retrospective cross-sectional single-center analysis of abdominal NCCT scans performed between 2012-20 for any indication in adult subjects. Images were analyzed using an automated deep learning liver segmentation and attenuation assessment algorithm to obtain a mean volumetric liver attenuation value. Image-based steatosis was defined as mean hepatic attenuation < 40 HU and compared to textual radiology reports. Manual review of a random subset of scans and reports was used to verify results. RESULTS: 3,646 NCCT scans from 2,710 adult patients were analyzed. The mean liver attenuation derived from the deep-learning algorithm was 50.4 ± 11.8 HU. Image-based steatosis was found in 480 (13.1%) scans, with a mean liver attenuation of 29.8 ± 14 HU. Radiologists reported steatosis in only 157 (32.7%) of these low-attenuation scans. Predictors of unreported steatosis included higher average liver attenuation (even if <40 HU), high variability of fat distribution in the liver and low BMI. CONCLUSION: We found that incidental hepatic steatosis in non-contrast CT is reported in a minority of scans. Incorporating artificial intelligence-based hepatic attenuation measurement in CT scan reading may increase reporting rates.