Dataset Information

Quantitative analysis of contrast-enhanced ultrasonography: differentiating focal nodular hyperplasia from hepatocellular carcinoma.

ABSTRACT: OBJECTIVE: To explore the potential of quantitative analysis of contrast-enhanced ultrasonography (CEUS) in differentiating focal nodular hyperplasia (FNH) from hepatocellular carcinoma (HCC). METHODS: 34 cases of FNH and 66 cases of HCC (all lesions <5 cm) were studied using CEUS to evaluate enhancement patterns and using analytic software Sonoliver® (Image-Arena™ v.4.0, TomTec Imaging Systems, Munich, Germany) to obtain quantitative features of CEUS in the region of interest. The quantitative features of maximum of intensity (IMAX), rise slope (RS), rise time (RT) and time to peak (TTP) were compared between the two groups and applied to further characterise both FNH and HCC with hypoenhancing patterns in the late phase on CEUS. RESULTS: The sensitivity and specificity of CEUS for diagnosis of FNH were 67.6% and 93.9%, respectively. For quantitative analysis, IMAX and RS in FNHs were significantly higher than those in HCCs (p<0.05), while RT and TTP in FNHs were significantly shorter (p<0.05). Both the 11 FNHs and 62 HCCs with hypo-enhancing patterns in the late phase were further characterised with their quantitative features, and the sensitivity and specificity of IMAX for diagnosis of FNH were 90.9% and 43.5%, RS 81.8% and 80.6%, RT 90.9% and 71.0%, and TTP 90.9% and 71.0%, respectively. CONCLUSION: The quantitative features of CEUS in FNH and HCC were significantly different, and they could further differentiate FNH from HCC following conventional CEUS. ADVANCES IN KNOWLEDGE: Our findings suggest that quantitative analysis of CEUS can improve the accuracy of differentiating FNH from HCC.

SUBMITTER: Pei XQ

PROVIDER: S-EPMC3608056 | biostudies-other | 2013 Mar

REPOSITORIES: biostudies-other

ACCESS DATA

Similar Datasets

Project description:BackgroundThe typical enhancement patterns of hepatocellular carcinoma (HCC) on contrast-enhanced ultrasound (CEUS) are hyper-enhanced in the arterial phase and washed out during the portal venous and late phases. However, atypical variations make a differential diagnosis both challenging and crucial. We aimed to investigate whether machine learning-based ultrasonic signatures derived from CEUS images could improve the diagnostic performance in differentiating focal nodular hyperplasia (FNH) and atypical hepatocellular carcinoma (aHCC).Patients and methodsA total of 226 focal liver lesions, including 107 aHCC and 119 FNH lesions, examined by CEUS were reviewed retrospectively. For machine learning-based ultrasomics, 3,132 features were extracted from the images of the baseline, arterial, and portal phases. An ultrasomics signature was generated by a machine learning model. The predictive model was constructed using the support vector machine method trained with the following groups: ultrasomics features, radiologist's score, and combination of ultrasomics features and radiologist's score. The diagnostic performance was explored using the area under the receiver operating characteristic curve (AUC).ResultsA total of 14 ultrasomics features were chosen to build an ultrasomics model, and they presented good performance in differentiating FNH and aHCC with an AUC of 0.86 (95% confidence interval [CI]: 0.80, 0.89), a sensitivity of 76.6% (95% CI: 67.5%, 84.3%), and a specificity of 80.5% (95% CI: 70.6%, 85.9%). The model trained with a combination of ultrasomics features and the radiologist's score achieved a significantly higher AUC (0.93, 95% CI: 0.89, 0.96) than that trained with the radiologist's score (AUC: 0.84, 95% CI: 0.79, 0.89, P < 0.001). For the sub-group of HCC with normal AFP value, the model trained with a combination of ultrasomics features, and the radiologist's score remain achieved the highest AUC of 0.92 (95% CI: 0.87, 0.96) compared to that with the ultrasomics features (AUC: 0.86, 95% CI: 0.74, 0.89, P < 0.001) and radiologist's score (AUC: 0.86, 95% CI: 0.79, 0.91, P < 0.001).ConclusionsMachine learning-based ultrasomics performs as well as the staff radiologist in predicting the differential diagnosis of FNH and aHCC. Incorporating an ultrasomics signature into the radiologist's score improves the diagnostic performance in differentiating FNH and aHCC.

Project description:BackgroundCurrent practice guidelines recommend the use of ultrasound (US) as an initial surveillance tool for hepatocellular carcinoma (HCC) in patients with liver cirrhosis. Patients with liver cirrhosis, however, frequently have coarse liver parenchyma, masking the presence of tiny nodules during B-mode US. Contrast-enhanced US (CEUS) with Sonazoid has a long-lasting, stable Kupffer phase, which makes it possible to scan the entire liver to depict small lesions. In addition, defect reperfusion imaging (reinjection imaging) enables to determine whether the detected nodule is HCC or not. This prospective, multicenter, randomized, controlled trial was conducted to demonstrate the usefulness of Kupffer phase surveillance in the detection of small HCC compared to B-mode US.MethodsA total of 23 institutions joined this study. In total, 656 patients with hepatitis B- or C-related liver cirrhosis were randomized either to the B-mode US surveillance group (n = 313) or the Kupffer phase CEUS with Sonazoid surveillance group (n = 309). The primary endpoint was the maximum size of HCC at the time of the first detection. Secondary endpoints included time to HCC detection, number of tumors, and Barcelona Clinic Liver Cancer stage at the first detection, and sensitivity, specificity, and accuracy of each method in the diagnosis, and the cumulative detection rate of HCC.ResultsThe mean HCC size at the first detection was significantly smaller in the CEUS (13.0 ± 4.1 mm; n = 28) than in the B-mode US group (16.7 ± 4.1 mm; n = 26) (p = 0.011). Of the 38 patients with HCV cirrhosis diagnosed with HCC by US alone, mean tumor size at the first detection was significantly smaller in the 20 patients diagnosed by CEUS alone than in the 18 diagnosed by B-mode US alone (12.7 ± 3.1 vs. 17.6 ± 7.0 mm, p = 0.012). In contrast, among the 16 patients with HBV cirrhosis diagnosed by US alone, mean tumor size at the first detection was similar in the 8 patients diagnosed by CEUS alone and the 8 diagnosed by B-mode US (13.6 ± 6.0 vs. 14.5 ± 2.7 mm, p = 0.715).ConclusionKupffer phase CEUS surveillance with Sonazoid is extremely useful for the early detection and confirmation of HCC using a reinjection technique. Kupffer phase CEUS with Sonazoid contrast combined with the reinjection technique is, therefore, recommended as first-line screening tool for HCC in patients with liver cirrhosis, especially those with very coarse liver parenchyma.

Dataset Information

Quantitative analysis of contrast-enhanced ultrasonography: differentiating focal nodular hyperplasia from hepatocellular carcinoma.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets