OBJECTIVE: The objective of this study was to develop a combined model based on radiomics features of Sonazoid contrast-enhanced ultrasound (CEUS) during the Kupffer phase and to evaluate its value in differentiating well-differentiated hepatocellular carcinoma (w-HCC) from atypical benign focal liver lesions (FLLs).
METHODS: A total of 116 patients with preoperatively Sonazoid-CEUS confirmed w-HCC or benign FLL were selected from a prospective multiple study on the clinical application of Sonazoid in FLLs conducted from August 2020 to March 2021. According to the randomization principle, the patients were divided into a training cohort and a test cohort in a 7:3 ratio. Seventy-nine patients were used for establishing and training the radiomics model and combined model. In comparison, 37 patients were used for validating and comparing the performance of the models. The diagnostic efficacy of the models for w-HCC and atypical benign FLLs was evaluated using ROCs curves and decision curves. A combined model nomogram was created to assess its value in reducing unnecessary biopsies.
RESULTS: Among the patients, there were 55 cases of w-HCC and 61 cases of atypical benign FLLs, including 28 cases of early liver abscess, 16 cases of atypical hepatic hemangioma, 8 cases of hepatocellular dysplastic nodules (DN), and 9 cases of focal nodular hyperplasia (FNH). The radiomics model and combined model we established had AUCs of 0.905 and 0.951, respectively, in the training cohort, and the AUCs of the two models in the test cohort were 0.826 and 0.912, respectively. The combined model outperformed the radiomics feature model significantly. Decision curve analysis demonstrated that the combined model achieved a higher net benefit within a specific threshold probability range (0.25 to 1.00). A nomogram of the combined model was developed.
CONCLUSIONS: The combined model based on the radiomics features of Sonazoid-CEUS in the Kupffer phase showed satisfactory performance in diagnosing w-HCC and atypical benign FLLs. It can assist clinicians in timely detecting malignant FLLs and reducing unnecessary biopsies for benign diseases.

Liver tumors constitute a major part of the global disease burden, often making regular imaging follow-up necessary. Recently, deep learning (DL) has increasingly been applied in this research area. How these methods could facilitate report writing is still a question, which our study aims to address by assessing multiple DL methods using the Medical Open Network for Artificial Intelligence (MONAI) framework, which may provide clinicians with preliminary information about a given liver lesion. For this purpose, we collected 2274 three-dimensional images of lesions, which we cropped from gadoxetate disodium enhanced T1w, native T1w, and T2w magnetic resonance imaging (MRI) scans. After we performed training and validation using 202 and 65 lesions, we selected the best performing model to predict features of lesions from our in-house test dataset containing 112 lesions. The model (EfficientNetB0) predicted 10 features in the test set with an average area under the receiver operating characteristic curve (standard deviation), sensitivity, specificity, negative predictive value, positive predictive value of 0.84 (0.1), 0.78 (0.14), 0.86 (0.08), 0.89 (0.08) and 0.71 (0.17), respectively. These results suggest that AI methods may assist less experienced residents or radiologists in liver MRI reporting of focal liver lesions.

OBJECTIVE: The detection and characterization of focal liver lesions (FLLs) in patients with cirrhosis is challenging. Accurate information about FLLs is key to their management, which can range from conservative methods to surgical excision. We sought to develop a nomogram that incorporates clinical risk factors, blood indicators, and enhanced computed tomography (CT) imaging findings to predict the nature of FLLs in cirrhotic livers.
METHODS: A total of 348 surgically confirmed FLLs were included. CT findings and clinical data were assessed. All factors with P < 0.05 in univariate analysis were included in multivariate analysis. ROC analysis was performed, and a nomogram was constructed based on the multivariate logistic regression analysis results.
RESULTS: The FLLs were either benign (n = 79) or malignant (n = 269). Logistic regression evaluated independent factors that positively affected malignancy. AFP (OR = 10.547), arterial phase hyperenhancement (APHE) (OR = 740.876), washout (OR = 0.028), satellite lesions (OR = 15.164), ascites (OR = 156.241), and nodule-in-nodule architecture (OR =27.401) were independent predictors of malignancy. The combined predictors had excellent performance in differentiating benign and malignant lesions, with an AUC of 0.959, a sensitivity of 95.24%, and a specificity of 87.5% in the training cohort and AUC of 0.981, sensitivity of 94.74%, and specificity of 93.33% in the test cohort. The C-index was 96.80%, and calibration curves showed good agreement between the nomogram predictions and the actual data.
CONCLUSIONS: The nomogram showed excellent discrimination and calibration for malignancy risk prediction, and it may aid in making FLLs treatment decisions.

BACKGROUND: Current advancements in dynamic contrast imaging of the liver have enabled increased sensitivity in the diagnosis of liver lesions. Evaluation and characterisation of the enhancement pattern of liver lesions in respect to the liver parenchyma aids in making a specific diagnosis.
OBJECTIVE: The aim of this study was to determine the liver findings on dynamic contrast computed tomography (CT) scanning and correlate them with clinicopathologic findings.
METHODS: This prospective cross-sectional study included 61 patients and took place between August 2017 and February 2018. Dynamic contrast CT was performed and the images were evaluated by two experienced radiologists. Correlation of the CT findings with histology results from an ultrasound-guided biopsy was done. Data analysis was performed using SPSS version 20.0.
RESULTS: Hepatocellular carcinoma (HCC) was the most common malignant lesion seen and showed three patterns of enhancement: homogenous, abnormal internal vessels and heterogeneous enhancement. Abnormal internal vessel pattern was most specific (90.6%) and showed a high positive predictive value (PPV) of 78.6%. Rapid washout showed a specificity of 87.5% and a PPV of 72.2% in the diagnosis of HCC. Dynamic contrast CT scan had a sensitivity of 93%, specificity of 50%, PPV of 91% and diagnostic accuracy of 95.5% in differentiation of benign and malignant liver lesions. Considering only Liver Imaging Reporting and Data System (LI-RADS) category 5 as conclusive for HCC diagnosis, our study did not miss a significant number of HCCs. Liver Imaging Reporting and Data System category 5 showed specificity of 81.3% and PPV of 75%.
CONCLUSIONS: Enhancement patterns on a dynamic contrast CT scan of the liver are useful in the interpretation of CT images for specific diagnoses.

OBJECTIVE: This study aimed to compare the efficacy of Sonazoid and SonoVue in subjects with focal liver lesions.
METHODS: The patients who had untreated focal solid liver lesions confirmed by B-mode ultrasonography were eligible for the study. The target lesion and whole liver were scanned by gray scale ultrasonography; then, contrast-enhanced ultrasonography was performed, and the results were evaluated blindly. The main end point was accuracy improvement with postcontrast versus precontrast ultrasound examination for diagnosis of the target lesion of interest as malignant or benign against the reference standard.
RESULTS: There were 65 patients with 65 hepatic tumors enrolled in the study. The improvement of diagnostic accuracy was 0.30 in the Sonazoid group and 0.16 in the SonoVue group (95% confidence interval, -0.828-0.168; P = .24). Using 20% as the noninferiority margin, the upper limit of the 95% confidence interval (0.168) was less than 0.20. The number of lesions detected during the whole-liver scanning in the Sonazoid group was significantly more than that detected in the SonoVue group (P = .024).
CONCLUSIONS: The diagnosis value of Sonazoid is noninferior to SonoVue, and this new contrast agent can improves the whole-liver image quality.

OBJECTIVE: To determine the optimal bolus injection rate of ultrasound (US) contrast agent in vascular imaging for focal liver lesions.
METHODS: Thirteen patients with 13 focal liver lesions (5 hepatocellular carcinomas (HCCs) with cirrhosis, 4 liver metastases, 2 hemangiomas, 1 intrahepatic cholangiocarcinoma, 1 focal nodular hyperplasia) received two bolus injections of Sonazoid (at 0.5 and 2.0 mL/s) using an automatic power injector. The lesion-to-liver contrast ratio at peak enhancement was quantitatively evaluated. Enhancement of the lesions compared to liver parenchyma was assessed by two independent readers using a five-point scale and qualitatively evaluated by receiver operating characteristic (ROC) analysis.
RESULTS: For all lesions, the contrast ratio was not significantly different between the two injection rates. For HCCs, the contrast ratio was higher at 0.5 mL/s (7.41 ± 6.56) than at 2.0 mL/s (4.28 ± 4.66, p = 0.025). For all lesions, the mean area under the ROC curve (AUC) was not significantly different between the two injection rates. For HCCs, the AUC was greater at 0.5 mL/s than at 2.0 mL/s (AUC: 0.86, p = 0.013).
CONCLUSIONS: In contrast-enhanced US, an injection rate of 0.5 mL/s is superior to an injection rate of 2.0 mL/s for the quantitative and qualitative analysis of HCCs in the cirrhotic liver.