Computer-aided diagnosis for estimating the malignancy grade of hepatocellular carcinoma using contrast-enhanced ultrasound: an ROC observer study

A combined model based on radiomics features of Sonazoid contrast-enhanced ultrasound in the Kupffer phase for the diagnosis of well-differentiated hepatocellular carcinoma and atypical focal liver lesions: a prospective, multicenter study

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.

CONCLUSION

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.

Diagnostic Performance of an Artificial Intelligence Model Based on Contrast-Enhanced Ultrasound in Patients with Liver Lesions: A Comparative Study with Clinicians

Contrast-enhanced ultrasound (CEUS) is widely used in the characterization of liver tumors; however, the evaluation of perfusion patterns using CEUS has a subjective character. This study aims to evaluate the accuracy of an automated method based on CEUS for classifying liver lesions and to compare its performance with that of two experienced clinicians. The system used for automatic classification is based on artificial intelligence (AI) algorithms. For an interpretation close to the clinical setting, both clinicians knew which patients were at high risk for hepatocellular carcinoma (HCC), but only one was aware of all the clinical data. In total, 49 patients with 59 liver tumors were included. For the benign and malignant classification, the AI model outperformed both clinicians in terms of specificity (100% vs. 93.33%); still, the sensitivity was lower (74% vs. 93.18% vs. 90.91%). In the second stage of multiclass diagnosis, the automatic model achieved a diagnostic accuracy of 69.93% for HCC and 89.15% for liver metastases. Readers demonstrated greater diagnostic accuracy for HCC (83.05% and 79.66%) and liver metastases (94.92% and 96.61%) compared to the AI system; however, both were experienced sonographers. The AI model could potentially assist and guide less-experienced clinicians to discriminate malignant from benign liver tumors with high accuracy and specificity.

Non-invasive preoperative prediction of Edmondson-Steiner grade of hepatocellular carcinoma based on contrast-enhanced ultrasound using ensemble learning

Purpose

This study aimed to explore the clinical value of non-invasive preoperative Edmondson-Steiner grade of hepatocellular carcinoma (HCC) using contrast-enhanced ultrasound (CEUS).

Methods

212 cases of HCCs were retrospectively included, including 83 cases of high-grade HCCs and 129 cases of low-grade HCCs. Three representative CEUS images were selected from the arterial phase, portal vein phase, and delayed phase and stored in a 3-dimensional array. ITK-SNAP was used to segment the tumor lesions manually. The Radiomics method was conducted to extract high-dimensional features on these contrast-enhanced ultrasound images. Then the independent sample T-test and the Least Absolute Shrinkage and Selection Operator (LASSO) were employed to reduce the feature dimensions. The optimized features were modeled by a classifier based on ensemble learning, and the Edmondson Steiner grading was predicted in an independent testing set using this model.

Results

A total of 1338 features were extracted from the 3D images. After the dimension reduction, 10 features were finally selected to establish the model. In the independent testing set, the integrated model performed best, with an AUC of 0.931.

Conclusion

This study proposed an Edmondson-Steiner grading method for HCC with CEUS. The method has good classification performance on independent testing sets, which can provide quantitative analysis support for clinical decision-making.

Interpretable Machine Learning for Characterization of Focal Liver Lesions by Contrast-Enhanced Ultrasound

This work proposes an interpretable radiomics approach to differentiate between malignant and benign focal liver lesions (FLLs) on contrast-enhanced ultrasound (CEUS). Although CEUS has shown promise for differential FLLs diagnosis, current clinical assessment is performed only by qualitative analysis of the contrast enhancement patterns. Quantitative analysis is often hampered by the unavoidable presence of motion artifacts and by the complex, spatiotemporal nature of liver contrast enhancement, consisting of multiple, overlapping vascular phases. To fully exploit the wealth of information in CEUS, while coping with these challenges, here we propose combining features extracted by the temporal and spatiotemporal analysis in the arterial phase enhancement with spatial features extracted by texture analysis at different time points. Using the extracted features as input, several machine learning classifiers are optimized to achieve semiautomatic FLLs characterization, for which there is no need for motion compensation and the only manual input required is the location of a suspicious lesion. Clinical validation on 87 FLLs from 72 patients at risk for hepatocellular carcinoma (HCC) showed promising performance, achieving a balanced accuracy of 0.84 in the distinction between benign and malignant lesions. Analysis of feature relevance demonstrates that a combination of spatiotemporal and texture features is needed to achieve the best performance. Interpretation of the most relevant features suggests that aspects related to microvascular perfusion and the microvascular architecture, together with the spatial enhancement characteristics at wash-in and peak enhancement, are important to aid the accurate characterization of FLLs.

Preoperative Pathological Grading of Hepatocellular Carcinoma Using Ultrasomics of Contrast-Enhanced Ultrasound

RATIONALE AND OBJECTIVES

To develop an ultrasomics model for preoperative pathological grading of hepatocellular carcinoma (HCC) using contrast-enhanced ultrasound (CEUS).

MATERIAL AND METHODS

A total of 235 HCCs were retrospectively enrolled, including 65 high-grade and 170 low-grade HCCs. Representative images of four-phase CEUS were selected from the baseline sonography, arterial, portal venous, and delayed phase images. Tumor ultrasomics features were automatically extracted using Ultrasomics-Platform software. Models were built via the classifier support vector machine, including an ultrasomics model using the ultrasomics features, a clinical model using the clinical factors, and a combined model using them both. Model performances were tested in the independent validation cohort considering efficiency and clinical usefulness.

RESULTS

A total of 1502 features were extracted from each image. After the reproducibility test and dimensionality reduction, 25 ultrasomics features and 3 clinical factors were selected to build the models. In the validation cohort, the combined model showed the best predictive power, with an area under the curve value of 0.785 (95% confidence interval [CI] 0.662-0.909), compared to the ultrasomics model of 0.720 (95% CI 0.576-0.864) and the clinical model of 0.665 (95% CI 0.537-0.793). Decision curve analysis suggested that the combined model was clinically useful, with a corresponding net benefit of 0.760 compared to the other two models.

CONCLUSION

We presented an ultrasomics-clinical model based on multiphase CEUS imaging and clinical factors, which showed potential value for the preoperative discrimination of HCC pathological grades.

Dynamic Contrast-Enhanced Ultrasound Radiomics for Hepatocellular Carcinoma Recurrence Prediction After Thermal Ablation

PURPOSE

To develop a radiomics model based on dynamic contrast-enhanced ultrasound (CEUS) to predict early and late recurrence in patients with a single HCC lesion ≤ 5 cm in diameter after thermal ablation.

PROCEDURES

We enrolled patients who underwent thermal ablation for HCC in our hospital from April 2004 to April 2017. Radiomics based on two branch convolution recurrent network was utilized to analyze preoperative dynamic CEUS image of HCC lesions to establish CEUS model, in comparison to the conventional ultrasound (US), clinical, and combined models. Clinical follow-up of HCC recurrence after ablation were taken as reference standard to evaluate the predicted performance of CEUS model and other models.

RESULTS

We finally analyzed 318 patients (training cohort: test cohort = 255:63). The combined model showed better performance for early recurrence than CUES (in training cohort, AUC, 0.89 vs. 0.84, P < 0.001; in test cohort, AUC, 0.84 vs. 0.83, P = 0.272), US (P < 0.001), or clinical model (P < 0.001). For late recurrence prediction, the combined model showed the best performance than the CEUS (C-index, in training cohort, 0.77 vs. 0.76, P = 0.009; in test cohort, 0.77 vs. 0.68, P < 0.001), US (P < 0.001), or clinical model (P < 0.001).

CONCLUSIONS

The CEUS model based on dynamic CEUS radiomics performed well in predicting early HCC recurrence after ablation. The combined model combining CEUS, US radiomics, and clinical factors could stratify the high risk of late recurrence.

Advances in diagnostic application of ultrasomics in liver lesions

With the progress of medical technology in recent years, radiomics has been rapidly developed and widely used. Ultrasomics, as a branch of radiomics, is gradually applied to liver cancer, breast cancer, and other fields, and some research results have been acknowledged by clinicians. In the study of liver lesions, ultrasound is a vital diagnostic imaging method, but it also has limitations. For example, its performance is inferior to computed tomography or magnetic resonance imaging with regard to the diagnostic specificity for benignity and malignancy. The introduction and progress of ultrasomics provide new methods and ideas that could improve the ability to identify benignity or malignancy of liver lesions, tumor stage, and prognosis of the disease.

Current role of ultrasound in the diagnosis of hepatocellular carcinoma

Ultrasonography (US) is a major, sustainable hepatocellular carcinoma (HCC) surveillance method as it provides inexpensive, real-time, and noninvasive detection. Since US findings are based on pathological features, knowledge of pathological features is essential for delivering a correct US diagnosis. Recent advances in US equipment have made it possible to provide more information, such as malignancy potential and accurate localization diagnosis of HCC. Evaluation of malignancy potential is important to determine the treatment strategy, especially for small HCC. Diagnosis of blood flow dynamics using color Doppler and contrast-enhanced US is one of the most definitive approaches for evaluating HCC malignancy potential. Recently, a new Doppler microvascular imaging technique, superb microvascular imaging, which can detect Doppler signals generated by low-velocity blood flow, was developed. A fusion imaging system, another innovative US technology, has already become an indispensable technology over the last few years not only for US-guided radiofrequency ablation but also for the detection of small, invisible HCC. This article reviews the evidence on the use of ultrasound and contrast-enhanced ultrasound with Sonazoid for the practical management of HCC.

Comparison Between Low Mechanical Index and High Mechanical Index Contrast Modes of Contrast-Enhanced Ultrasonography: Evaluation of Perfusion Defects of Hypervascular Hepatocellular Carcinomas During the Post-Vascular Phase

OBJECTIVES

We evaluated the detection rates for perfusion defects in hypervascular hepatocellular carcinomas comparing the low mechanical index (MI) and high MI contrast modes during the post-vascular phase (PVP) of contrast-enhanced ultrasonography.

METHODS

Seventy-eight patients with 84 hypervascular hepatocellular carcinomas (mean diameter, 23.4 ± 11.2 mm) were selected for this retrospective study. All the patients underwent whole-liver scanning using conventional ultrasonography before injection of a perflubutane-based contrast agent (Sonazoid), and all the detected nodules were classified as either hypoechoic or hyperechoic nodules. Next, hypoechoic and hyperechoic nodules were evaluated using contrast-enhanced ultrasonography, and the presence of a perfusion defect was assessed for each nodule using both the low MI (0.2-0.3) and the high MI (0.7-1.2) contrast modes during the PVP (10 minutes after injection). The data were analyzed using the McNemar test.

RESULTS

Forty-four nodules were classified as hypoechoic nodules, and the remaining 40 nodules were classified as hyperechoic nodules using conventional ultrasonography. The detection rate for perfusion defects determined using the high MI contrast mode was higher than that determined using the low MI contrast mode in hyperechoic nodules during the PVP (low MI, 58% [23 of 40]; high MI, 90% [36 of 40]; P < .0001). However, no significant difference was observed between the low MI and the high MI contrast modes in hypoechoic nodules (low MI, 80% [35 of 44]; high MI, 89% [39 of 44]; P = .125).

CONCLUSION

Compared with the low MI contrast mode, the high MI contrast mode was more sensitive for detecting perfusion defects in hypervascular hepatocellular carcinomas in patients with hyperechoic nodules during the PVP.

Preoperative diagnosis and prediction of hepatocellular carcinoma: Radiomics analysis based on multi-modal ultrasound images

BACKGROUND

This study aims to establish a radiomics analysis system for the diagnosis and clinical behaviour prediction of hepatocellular carcinoma (HCC) based on multi-parametric ultrasound imaging.

METHODS

A total of 177 patients with focal liver lesions (FLLs) were included in the study. Every patient underwent multi-modal ultrasound examination, including B-mode ultrasound (BMUS), shear wave elastography (SWE), and shear wave viscosity (SWV) imaging. The radiomics analysis system was built on sparse representation theory (SRT) and support vector machine (SVM) for asymmetric data. Through the sparse regulation from the SRT, the proposed radiomics system can effectively avoid over-fitting issues that occur in regular radiomics analysis. The purpose of the proposed system includes differential diagnosis between benign and malignant FLLs, pathologic diagnosis of HCC, and clinical prognostic prediction. Three biomarkers, including programmed cell death protein 1 (PD-1), antigen Ki-67 (Ki-67) and microvascular invasion (MVI), were included and analysed. We calculated the accuracy (ACC), sensitivity (SENS), specificity (SPEC) and area under the receiver operating characteristic curve (AUC) to evaluate the performance of the radiomics models.

RESULTS

A total of 2560 features were extracted from the multi-modal ultrasound images for each patient. Five radiomics models were built, and leave-one-out cross-validation (LOOCV) was used to evaluate the models. In LOOCV, the AUC was 0.94 for benign and malignant classification (95% confidence interval [CI]: 0.88 to 0.98), 0.97 for malignant subtyping (95% CI: 0.93 to 0.99), 0.97 for PD-1 prediction (95% CI: 0.89 to 0.98), 0.94 for Ki-67 prediction (95% CI: 0.87 to 0.97), and 0.98 for MVI prediction (95% CI: 0.93 to 0.99). The performance of each model improved when the viscosity modality was included.

CONCLUSIONS

Radiomics analysis based on multi-modal ultrasound images could aid in comprehensive liver tumor evaluations, including diagnosis, differential diagnosis, and clinical prognosis.

A two-stage multi-view learning framework based computer-aided diagnosis of liver tumors with contrast enhanced ultrasound images

OBJECTIVE

With the fast development of artificial intelligence techniques, we proposed a novel two-stage multi-view learning framework for the contrast-enhanced ultrasound (CEUS) based computer-aided diagnosis for liver tumors, which adopted only three typical CEUS images selected from the arterial phase, portal venous phase and late phase.

MATERIALS AND METHODS

In the first stage, the deep canonical correlation analysis (DCCA) was performed on three image pairs between the arterial and portal venous phases, arterial and delayed phases, and portal venous and delayed phases respectively, which then generated total six-view features. While in the second stage, these multi-view features were then fed to a multiple kernel learning (MKL) based classifier to further promote the diagnosis result. Two MKL classification algorithms were evaluated in this MKL-based classification framework. We evaluated proposed DCCA-MKL framework on 93 lesions (47 malignant cancers vs. 46 benign tumors).

RESULTS

The proposed DCCA-MKL framework achieved the mean classification accuracy, sensitivity, specificity, Youden index, false positive rate, and false negative rate of 90.41 ± 5.80%, 93.56 ± 5.90%, 86.89 ± 9.38%, 79.44 ± 11.83%, 13.11 ± 9.38% and 6.44 ± 5.90%, respectively, by soft margin MKL classifier.

CONCLUSION

The experimental results indicate that the proposed DCCA-MKL framework achieves best performance for discriminating benign liver tumors from malignant liver cancers. Moreover, it is also proved that the three-phase CEUS image based CAD is feasible for liver tumors with the proposed DCCA-MKL framework.

Focal Liver Lesions: Computer-aided Diagnosis by Using Contrast-enhanced US Cine Recordings

Purpose To assess the performance of computer-aided diagnosis (CAD) systems and to determine the dominant ultrasonographic (US) features when classifying benign versus malignant focal liver lesions (FLLs) by using contrast material-enhanced US cine clips. Materials and Methods One hundred six US data sets in all subjects enrolled by three centers from a multicenter trial that included 54 malignant, 51 benign, and one indeterminate FLL were retrospectively analyzed. The 105 benign or malignant lesions were confirmed at histologic examination, contrast-enhanced computed tomography (CT), dynamic contrast-enhanced magnetic resonance (MR) imaging, and/or 6 or more months of clinical follow-up. Data sets included 3-minute cine clips that were automatically corrected for in-plane motion and automatically filtered out frames acquired off plane. B-mode and contrast-specific features were automatically extracted on a pixel-by-pixel basis and analyzed by using an artificial neural network (ANN) and a support vector machine (SVM). Areas under the receiver operating characteristic curve (AUCs) for CAD were compared with those for one experienced and one inexperienced blinded reader. A third observer graded cine quality to assess its effects on CAD performance. Results CAD, the inexperienced observer, and the experienced observer were able to analyze 95, 100, and 102 cine clips, respectively. The AUCs for the SVM, ANN, and experienced and inexperienced observers were 0.883 (95% confidence interval [CI]: 0.793, 0.940), 0.829 (95% CI: 0.724, 0.901), 0.843 (95% CI: 0.756, 0.903), and 0.702 (95% CI: 0.586, 0.782), respectively; only the difference between SVM and the inexperienced observer was statistically significant. Accuracy improved from 71.3% (67 of 94; 95% CI: 60.6%, 79.8%) to 87.7% (57 of 65; 95% CI: 78.5%, 93.8%) and from 80.9% (76 of 94; 95% CI: 72.3%, 88.3%) to 90.3% (65 of 72; 95% CI: 80.6%, 95.8%) when CAD was in agreement with the inexperienced reader and when it was in agreement with the experienced reader, respectively. B-mode heterogeneity and contrast material washout were the most discriminating features selected by CAD for all iterations. CAD selected time-based time-intensity curve (TIC) features 99.0% (207 of 209) of the time to classify FLLs, versus 1.0% (two of 209) of the time for intensity-based features. None of the 15 video-quality criteria had a statistically significant effect on CAD accuracy-all P values were greater than the Holm-Sidak α-level correction for multiple comparisons. Conclusion CAD systems classified benign and malignant FLLs with an accuracy similar to that of an expert reader. CAD improved the accuracy of both readers. Time-based features of TIC were more discriminating than intensity-based features. ^© RSNA, 2017 Online supplemental material is available for this article.

Computer-Aided Diagnosis of Focal Liver Lesions Using Contrast-Enhanced Ultrasonography With Perflubutane Microbubbles

This paper proposes an automatic classification method based on machine learning in contrast-enhanced ultrasonography (CEUS) of focal liver lesions using the contrast agent Sonazoid. This method yields spatial and temporal features in the arterial phase, portal phase, and post-vascular phase, as well as max-hold images. The lesions are classified as benign or malignant and again as benign, hepatocellular carcinoma (HCC), or metastatic liver tumor using support vector machines (SVM) with a combination of selected optimal features. Experimental results using 98 subjects indicated that the benign and malignant classification has 94.0% sensitivity, 87.1% specificity, and 91.8% accuracy, and the accuracy of the benign, HCC, and metastatic liver tumor classifications are 84.4%, 87.7%, and 85.7%, respectively. The selected features in the SVM indicate that combining features from the three phases are important for classifying FLLs, especially, for the benign and malignant classifications. The experimental results are consistent with CEUS guidelines for diagnosing FLLs. This research can be considered to be a validation study, that confirms the importance of using features from these phases of the examination in a quantitative manner. In addition, the experimental results indicate that for the benign and malignant classifications, the specificity without the post-vascular phase features is significantly lower than the specificity with the post-vascular phase features. We also conducted an experiment on the operator dependency of setting regions of interest and observed that the intra-operator and inter-operator kappa coefficients were 0.45 and 0.77, respectively.