Background/Aims
Hepatocellular carcinoma (HCC) frequently recurs after curative treatment, posing challenges to long-term survival. Although contrast-enhanced multiphasic computed tomography (CECT) is commonly used for detecting recurrence, it is associated with risks such as radiation exposure and contrast agent reactions. This study aimed to compare the diagnostic performance of non-contrast magnetic resonance imaging (NC-MRI) with CECT for detecting recurrent HCC.
Methods
In this prospective multicenter intra-individual head-to-head comparison trial (study identifier: NCT05690451, KCT0006395), participants who had undergone curative treatment for HCC and remained recurrence-free for over two years were enrolled. Each participant underwent three follow-up imaging sessions at 2–6-month intervals using both CECT and NC-MRI. The primary outcome was the detection accuracy of each modality, analyzed using the generalized estimating equation analysis. Secondary outcomes included sensitivity and specificity.
Results
The study included 203 participants with a total of 528 paired imaging sessions, identifying recurrent HCC in 22 cases (10.8%). Among these, 21 cases involved intrahepatic recurrence with a median tumor size of 1.3 cm, and one case had aortocaval lymph node metastasis. NC-MRI achieved a detection accuracy of 96.6% (196/203), higher than CECT’s 91.6% (186/203) (P=0.006). NC-MRI also showed greater sensitivity (77.3% [17/22] vs. 36.4% [8/22]; P=0.012), while specificity was comparable between NC-MRI and CECT (98.9% [179/181] vs. 98.3% [178/181]; P=0.999).
Conclusions
NC-MRI demonstrated higher sensitivity and accuracy compared to CECT in detecting recurrent HCC in patients who had been disease-free for over two years following curative treatment, indicating its potential as a preferred imaging modality for this purpose.

Background/Aims
The prediction of clinical outcomes in patients with chronic hepatitis B (CHB) is paramount for effective management. This study aimed to evaluate the prognostic value of computed tomography (CT) analysis using deep learning algorithms in patients with CHB. Methods: This retrospective study included 2,169 patients with CHB without hepatic decompensation who underwent contrast-enhanced abdominal CT for hepatocellular carcinoma (HCC) surveillance between January 2005 and June 2016. Liver and spleen volumes and body composition measurements including subcutaneous adipose tissue (SAT), visceral adipose tissue (VAT), and skeletal muscle indices were acquired from CT images using deep learning-based fully automated organ segmentation algorithms. We assessed the significant predictors of HCC, hepatic decompensation, diabetes mellitus (DM), and overall survival (OS) using Cox proportional hazard analyses. Results: During a median follow-up period of 103.0 months, HCC (n=134, 6.2%), hepatic decompensation (n=103, 4.7%), DM (n=432, 19.9%), and death (n=120, 5.5%) occurred. According to the multivariate analysis, standardized spleen volume significantly predicted HCC development (hazard ratio [HR]=1.01, P=0.025), along with age, sex, albumin and platelet count. Standardized spleen volume (HR=1.01, P<0.001) and VAT index (HR=0.98, P=0.004) were significantly associated with hepatic decompensation along with age and albumin. Furthermore, VAT index (HR=1.01, P=0.001) and standardized spleen volume (HR=1.01, P=0.001) were significant predictors for DM, along with sex, age, and albumin. SAT index (HR=0.99, P=0.004) was significantly associated with OS, along with age, albumin, and MELD. Conclusions: Deep learning-based automatically measured spleen volume, VAT, and SAT indices may provide various prognostic information in patients with CHB.