Steatohepatitic hepatocellular carcinoma (SH-HCC) is a distinctive histologic variant of HCC for the presence of steatohepatitis. This study intended to evaluate the contrast-enhanced imaging features and clinicopathological characteristics of 26 SH-HCCs in comparison with 26 age-and-sex-matched non-SH-HCCs. The frequency of obesity (34.6%, p = 0.048) and type 2 diabetes mellitus (23.1%, p = 0.042) were significantly higher in SH-HCC patients. As seen via B-mode ultrasound (BMUS), SH-HCCs were predominantly hyperechoic (65.4%, p = 0.002) lesions, while non-SH-HCCs were mainly hypo-echoic. As seen via contrast-enhanced ultrasound (CEUS), 96.2% of SH-HCCs exhibited hyperenhancement in the arterial phase. During the portal venous and late phase, 88.5% of SH-HCCs showed late and mild washout. Consequently, most SH-HCCs and all non-SH-HCCs were categorized as LR-4 or LR-5. As seen via magnetic resonance imaging (MRI), a signal drop in the T1WI opposed-phase was observed in 84.6% of SH-HCCs (p = 0.000). Notably, diffuse fat in mass was detected in 57.7% (15/26) SH-HCCs (p < 0.001). As seen via contrast-enhanced MRI (CEMRI), most of the SH-HCCs and non-SH-HCCs exhibited heterogeneous hyperenhancement in the arterial phase (80.8% versus 69.2%, p = 0.337). During the delayed phase, 76.9% SH-HCCs and 88.5% non-SH-HCCs exhibited hypo-enhancement. Histopathologically, the rate of microvascular invasion (MVI) was significantly lower in SH-HCCs than non-SH-HCCs (42.3% versus 73.1%, p = 0.025). The frequency of hepatic steatosis >5% in non-tumoral liver parenchyma of SH-HCCs was significantly higher than in non-SH-HCCs (88.5% versus 26.9%, p = 0.000). Additionally, the fibrotic stages of S0, S1 and S2 in SH-HCCs were significantly higher than in non-SH-HCCs (p = 0.044). During follow-up, although the PFS of SH-HCC patients was significantly longer than non-SH-HCC patients (p = 0.046), for the overall survival rate of SH-HCC and non-SH-HCC patients there was no significant difference (p = 0.162). In conclusion, the frequency of metabolism-related diseases in SH-HCC patients was significantly higher than in non-SH-HCC patients. The imaging features of SH-HCCs combined the fatty change and typical enhancement performance of standard HCC as seen via CEUS/CEMRI.

Differential diagnosis of enlarged lymph nodes (ELNs) is essential for the treatment of related patients. Though multi-modal ultrasound including B-mode, Doppler ultrasound, elastography and contrast-enhanced ultrasound (CEUS) can enhance diagnostic performance for ELNs, the scenario of having only single or dual modal data is often encountered. In this study, an artificially intelligent diagnosis model based on the learning using privileged information was proposed to aid in differential diagnosis of ELNs in the case of single or dual modal images. In our model, B-mode, or combined with another modality, was used as the standard information (SI) and other modalities were used as the privileged information (PI). The model was constructed through the combination of the SI and PI in the training stage. By learning from the training samples, a random vector functional link network with privileged information (RVFL+) was obtained, which was used to classify the testing samples of solely the SI. Results showed that the accuracy, precision and Youden's index of the RVFL+ model, using B-mode with elastography as the SI and CEUS as the PI, reached 78.4%, 92.4% and 54.9%, increased by 14.0%, 8.4% and 24.5% compared with the model using B-mode as the SI without the PI. The method based on the LUPI can improve the diagnostic performance for ELNs.