A Nomogram Based on Combining Clinical Features and Contrast Enhanced Ultrasound LI-RADS Improves Prediction of Microvascular Invasion in Hepatocellular Carcinoma

The value of contrast-enhanced ultrasound combined with microflow imaging in predicting microvascular invasion of hepatocellular carcinoma before operation

OBJECTIVE

To evaluate the preoperative predictive value of contrast-enhanced ultrasound (CEUS) combined with microflow imaging (MFI) in microvascular invasion (MVI) of hepatocellular carcinoma (HCC).

METHODS

In our study, 80 patients with HCC were analyzed retrospectively. According to the gold standard of postoperative pathology, the patients were divided into MVI positive group (n = 39) and MVI negative group (n = 41). we were to analyze the correlation between CEUS and MVI in combination with MFI, to identify independent risk factors for the occurrence of MVI positive, and to analyze the predictive efficacy of every independent risk factor and their combination in preoperative prediction of MVI.

RESULTS

In our study, 80 patients were enrolled, including 39 patients in the MVI-positive group and 41 patients in the MVI-negative group, with a MVI-positive rate of 48.8%. By univariate analysis and multivariate analysis, it was found that there were statistically significant differences in enhancement range extension, start time of wash out and CEUS-MFI between the two groups, which were independent risk factors for MVI-positive. The combination of three independent risk factors is more effective than single one in predicting MVI of HCC.

CONCLUSIONS

CEUS combined with MFI is feasible for the preoperative prediction of MVI in HCC, and can provides meaningful help for individualized clinical treatment.

Clinical value of quantitative analysis of contrast-enhanced ultrasonography in the differential diagnosis of benign and malignant pelvic tumors

Background

Cervical cancer, endometrial cancer, and ovarian cancer are among the top 10 most common cancers in women, with ovarian cancer in particular being considered a "silent killer". Therefore, early detection, diagnosis, and treatment constitute important means of care for women's health. This study investigated the clinical value of the quantitative analysis of contrast-enhanced ultrasonography (CEUS) in the differential diagnosis of benign and malignant pelvic tumors.

Methods

CEUS was performed on 151 patients with pelvic masses. Subsequently, a qualitative diagnosis was completed using the image enhancement features and tumor parameters. A multiparametric analysis of CEUS images was performed, which included the following parameters: arrival time (AT), time to peak (TTP), peak intensity (PI), and ascent slope (AS). In addition, the qualitative diagnostic efficiency of CEUS was assessed in a multiparametric analysis, and the results were compared with pathological findings.

Results

The patients in the malignant group were older (P=0.001) and had larger lesion PI values (P<0.01) than those in the benign group. The PI difference (PId) and the AS difference (ASd) showed statistical differences (P<0.01) between the myometrium and lesion tissues in the same patient. Moreover, the PId and ASd showed the largest receiver operating characteristic (ROC) curve and area under the ROC curve (AUC), with sensitivities of 90.9% and 91.7% and specificities of 86.4% and 72.5%, respectively.

Conclusions

The quantitative analysis of CEUS provides a new, simpler, and more accurate method for the differential diagnosis of benign and malignant pelvic masses in clinical practice. The sensitivities and specificities of PId and ASd were higher compared to other parameters from the same patient.

Preoperative prediction of microvascular invasion in hepatocellular carcinoma using ultrasound features including elasticity

BACKGROUND

Microvascular invasion (MVI) is an important predictor of poor prognosis in patients with hepatocellular carcinoma (HCC). Accurate preoperative prediction of MVI in HCC would provide useful information to guide the choice of therapeutic strategy. Shear wave elastography (SWE) plays an important role in hepatic imaging, but its value in the preoperative prediction of MVI in HCC has not yet been proven.

AIM

To explore the value of conventional ultrasound features and SWE in the preoperative prediction of MVI in HCC.

METHODS

Patients with a postoperative pathological diagnosis of HCC and a definite diagnosis of MVI were enrolled in this study. Conventional ultrasound features and SWE features such as maximal elasticity (Emax) of HCCs and Emax of the periphery of HCCs were acquired before surgery. These features were compared between MVI-positive HCCs and MVI-negative HCCs and between mild MVI HCCs and severe MVI HCCs.

RESULTS

This study included 86 MVI-negative HCCs and 102 MVI-positive HCCs, including 54 with mild MVI and 48 with severe MVI. Maximal tumor diameters, surrounding liver tissue, color Doppler flow, Emax of HCCs, and Emax of the periphery of HCCs were significantly different between MVI-positive HCCs and MVI-negative HCCs. In addition, Emax of the periphery of HCCs was significantly different between mild MVI HCCs and severe MVI HCCs. Higher Emax of the periphery of HCCs and larger maximal diameters were independent risk factors for MVI, with odds ratios of 2.820 and 1.021, respectively.

CONCLUSION

HCC size and stiffness of the periphery of HCC are useful ultrasound criteria for predicting positive MVI. Preoperative ultrasound and SWE can provide useful information for the prediction of MVI in HCCs.

Contrast-Enhanced Ultrasound Liver Imaging Reporting and Data System in Hepatocellular Carcinoma ≤5 cm: Biological Characteristics and Patient Outcomes

Introduction

The present study aimed to evaluate the influence of biological characteristics of hepatocellular carcinoma (HCC) on the Liver Imaging Reporting and Data System (LI-RADS) v2017 category of contrast-enhanced ultrasound (CEUS) in patients with high risk and compare the outcomes among different categories after radical resection.

Methods

Between June 2017 and December 2020, standardized CEUS data of liver nodules were prospectively collected from multiple centers across China. We conducted a retrospective analysis of the prospectively collected data on HCCs measuring no more than 5 cm, as diagnosed by pathology. LI-RADS categories were assigned after thorough evaluation of CEUS features. Then, CEUS LI-RADS categories and major features were compared in different differentiation, Ki-67, and microvascular invasion (MVI) statuses. Differences in recurrence-free survival (RFS) among different LI-RADS categories were further analyzed.

Results

A total of 293 HCC nodules in 293 patients were included. This study revealed significant differences in the CEUS LI-RADS category of HCCs among differentiation (p < 0.001) and levels of Ki-67 (p = 0.01) and that poor differentiation (32.7% in LR-M, 12% in LR-5, and 6.2% in LR-4) (p < 0.001) and high level of Ki-67 (median value 30%) were more frequently classified into the LR-M category, whereas well differentiation (37.5% in LR-4, 15.1% in LR-5, and 11.5% in LR-M) and low levels of Ki-67 (median value 11%) were more frequently classified into the LR-4 category. No significant differences were found between MVI and CEUS LI-RADS categories (p > 0.05). With a median follow-up of 23 months, HCCs assigned to different CEUS LI-RADS classes showed no significant differences in RFS after resection.

Conclusions

Biological characteristics of HCC, including differentiation and level of Ki-67 expression, could influence major features of CEUS and impact the CEUS LI-RADS category. HCCs in different CEUS LI-RADS categories showed no significant differences in RFS after resection.

Predictive machine learning model for microvascular invasion identification in hepatocellular carcinoma based on the LI-RADS system

Purposes

This study aimed to establish a predictive model of microvascular invasion (MVI) in hepatocellular carcinoma (HCC) by contrast-enhanced computed tomography (CT), which relied on a combination of machine learning approach and imaging features covering Liver Imaging and Reporting and Data System (LI-RADS) features.

Methods

The retrospective study included 279 patients with surgery who underwent preoperative enhanced CT. They were randomly allocated to training set, validation set, and test set (167 patients vs. 56 patients vs. 56 patients, respectively). Significant imaging findings for predicting MVI were identified through the Least Absolute Shrinkage and Selection Operator (LASSO) logistic regression method. Predictive models were performed by machine learning algorithm, support vector machine (SVM), in the training set and validation set, and evaluated in the test set. Further, a combined model adding clinical findings to the radiologic model was developed. Based on the LI-RADS category, subgroup analyses were conducted.

Results

We included 116 patients with MVI which were diagnosed through pathological confirmation. Six imaging features were selected about MVI prediction: four LI-RADS features (corona enhancement, enhancing capsule, non-rim aterial phase hyperehancement, tumor size) and two non-LI-RADS features (internal arteries, non-smooth tumor margin). The radiological feature with the best accuracy was corona enhancement followed by internal arteries and tumor size. The accuracies of the radiological model and combined model were 0.725–0.714 and 0.802–0.732 in the training set, validation set, and test set, respectively. In the LR-4/5 subgroup, a sensitivity of 100% and an NPV of 100% were obtained by the high-sensitivity threshold. A specificity of 100% and a PPV of 100% were acquired through the high specificity threshold in the LR-M subgroup.

Conclusion

A combination of LI-RADS features and non-LI-RADS features and serum alpha-fetoprotein value could be applied as a preoperative biomarker for predicting MVI by the machine learning approach. Furthermore, its good performance in the subgroup by LI-RADS category may help optimize the management of HCC patients.

Contrast-enhanced ultrasonography for differential diagnosis of adnexal masses

Background

Quantitative contrast-enhanced ultrasonography parameters are affected by various factors. We evaluated corrected quantitative contrast enhanced ultrasonography in differentiating benign adnexal tumors from malignant tumors.

Methods

Patients with adnexal masses who underwent conventional and contrast-enhanced ultrasonography were included. Contrast-enhanced ultrasonography parameters such as base intensity, arrival time, peak intensity, time to peak intensity, ascending slope, and descending slope were measured. Corrected (time to peak intensity − arrival time) _mass/(time to peak intensity − arrival time) _uterus and (peak intensity − base intensity) _mass/(peak intensity − base intensity) _uterus were calculated. Lesions were confirmed by pathologic examination of surgical specimens.

Results

This study included 31 patients with 35 adnexal lesions including 20 (57.10%) benign and 15 (42.90%) malignant lesions. The corrected contrast-enhanced ultrasonography quantitative parameters in lesions were statistically different between malignant and benign groups (P<0.05). The optimal cut-off value for (time to peak intensity − arrival time) _mass/(time to peak intensity − arrival time) _uterus, ascending slope, and (peak intensity − base intensity) _mass/(peak intensity − base intensity) _uterus, and descending slope for differentiating malignant adnexal masses from benign tumors were 1.05 (area under curve: 0.93, P<0.05), 1.11 (area under curve: 0.83, P<0.05), 0.82 (area under curve: 0.73, P<0.05), and −0.27 (area under curve: 0.66, P=0.16), with sensitivity and specificity of 93.33% and 85.00%, 86.67% and 75.00%, 86.67% and 60.00%, and 54.55% and 66.67%, respectively.

Conclusions

Corrected contrast-enhanced ultrasonography parameters provide practical differential diagnosis value of adnexal lesions with high reliability for sonologists.

Combined clinical features and MRI parameters for the prediction of VEGFR2 in hepatocellular carcinoma patients

Purpose

To develop a prediction model for estimating the expression of vascular endothelial growth factor receptor 2 (VEGFR2) in hepatocellular carcinoma (HCC) patients using clinical features and the contrast-enhanced MRI Liver Imaging Reporting and Data System (LI-RADS).

Methods

A total of 206 HCC patients were subjected to preoperative contrast-enhanced MRI, radical resection, and VEGFR2 immunohistochemistry labeling. The intensity of VEGFR2 expression was used to split patients into either the positive group or the negative group. For continuous data, the Mann-Whitney U test was employed, and for categorical variables, the χ2 test was utilized.

Results

VEGFR2-positivity was identified in 41.7% (86/206) of the patients. VEGFR2-positive HCCs were confirmed by higher serum alpha-fetoprotein (AFP) levels, larger tumor dimensions (either on MRI or upon final pathology), and a higher LI-RADS score (all p < 0.001). LI-RADS scores and AFP levels were independent predictors for high VEGFR2 expression. These two parameters were used to establish a VEGFR2-positive risk nomogram, which was validated to possess both good discrimination and calibration. The area under the curve was 0.830 (sensitivity 83.6%, specificity 72.5%) and the mean absolute error was 0.021. The threshold probabilities ranged between 0.07 and 0.95, and usage of the model contributed net benefits.

Conclusion

A nomogram including clinical features and contrast-enhanced MRI parameters was developed and was demonstrably effective at predicting VEGFR2 expression in HCC patients.

Prediction of early recurrence of HCC after hepatectomy by contrast-enhanced ultrasound-based deep learning radiomics

Objective

This study aims to evaluate the predictive model based on deep learning (DL) and radiomics features from contrast-enhanced ultrasound (CEUS) to predict early recurrence (ER) in patients with hepatocellular carcinoma (HCC).

Methods

One hundred seventy-two patients with HCC who underwent hepatectomy and followed up for at least 1 year were included in this retrospective study. The data were divided according to the 7:3 ratios of training and test data. The ResNet-50 architecture, CEUS-based radiomics, and the combined model were used to predict the early recurrence of HCC after hepatectomy. The receiver operating characteristic (ROC) curve and calibration curve were drawn to evaluate its diagnostic efficiency.

Results

The CEUS-based radiomics ROCs of the “training set” and “test set” were 0.774 and 0.763, respectively. The DL model showed increased prognostic value, the ROCs of the “training set” and “test set” were 0.885 and 0.834, respectively. The combined model ROCs of the “training set” and “test set” were 0.943 and 0.882, respectively.

Conclusion

The deep learning radiomics model integrating DL and radiomics features from CEUS was used to predict ER and achieve satisfactory performance. Its diagnostic efficiency is significantly better than that of the single model.

Contrast-enhanced ultrasound for the diagnosis of hepatocellular carcinoma in adults with chronic liver disease

BACKGROUND

Hepatocellular carcinoma occurs mostly in people with chronic liver disease. Worldwide, it ranks sixth in terms of incidence of cancer, and fourth in terms of cancer-related deaths. Contrast-enhanced ultrasound (CEUS) is used as an add-on test to confirm the presence of focal liver lesions suspected as hepatocellular carcinoma after prior diagnostic tests such as abdominal ultrasound or measurement of alpha-foetoprotein, or both. According to guidelines, a single contrast-enhanced imaging investigation, with either computed tomography (CT) or magnetic resonance imaging (MRI), may show the typical hepatocellular carcinoma hallmarks in people with cirrhosis, which will be sufficient to diagnose hepatocellular carcinoma. However, a significant number of hepatocellular carcinomas show atypical imaging features, and therefore, are missed at imaging. Dynamic CEUS images are obtained similarly to CT and MRI images. CEUS differentiates between arterial and portal venous phases, in which sonographic hepatocellular carcinoma hallmarks, such as arterial hyperenhancement and subsequent washout appearance, are investigated. The advantages of CEUS over CT and MRI include real-time imaging, use of contrast agents that do not contain iodine and are not nephrotoxic, and quick image acquisition. Despite the advantages, the use of CEUS in the diagnostic algorithm for HCC remains controversial, with disagreement on relevant guidelines. There is no clear evidence of the benefit of surveillance programmes in terms of overall survival as the conflicting results can be a consequence of an inaccurate detection, ineffective treatment, or both. Therefore, assessing the diagnostic accuracy of CEUS may clarify whether the absence of benefit could be related to underdiagnosis. Furthermore, an assessment of the accuracy of CEUS for the diagnosis of hepatocellular carcinoma is needed for either diagnosing hepatocellular carcinoma or ruling it out in people with chronic liver disease who are not included in surveillance programmes.

OBJECTIVES

1. To assess the diagnostic accuracy of contrast-enhanced ultrasound (CEUS) for the diagnosis of hepatocellular carcinoma of any size and at any stage in adults with chronic liver disease, in a surveillance programme or in a clinical setting. 2. To assess the diagnostic accuracy of CEUS for the diagnosis of resectable hepatocellular carcinoma in people with chronic liver disease and identify potential sources of heterogeneity in the results.

SEARCH METHODS

We used standard, extensive Cochrane search methods. The last date of search was 5 November 2021.

SELECTION CRITERIA

We included studies assessing the diagnostic accuracy of CEUS for the diagnosis of hepatocellular carcinoma in adults with chronic liver disease, with cross-sectional designs, using one of the acceptable reference standards, such as pathology of the explanted liver, and histology of resected or biopsied focal liver lesion with at least a six-month follow-up.

DATA COLLECTION AND ANALYSIS

We used standard Cochrane methods to screen studies, extract data, and assess the risk of bias and applicability concerns, using the QUADAS-2 checklist. We used the bivariate model and provided estimates of summary sensitivity and specificity. We assessed the certainty of the evidence using GRADE. We presented uncertainty-of-the-accuracy estimates using 95% confidence intervals (CIs).

MAIN RESULTS

We included 23 studies with 6546 participants. Studies were published between 2001 and 2021. We judged all 23 studies at high-risk of bias in at least one domain, and 13/23 studies at high concern for applicability. Most studies used different reference standards to exclude the presence of the target condition. The time interval between the index test and the reference standard was rarely defined. We also had major concerns on their applicability due to the characteristics of the participants. - CEUS for hepatocellular carcinoma of any size and stage: sensitivity 77.8% (95% CI 69.4% to 84.4%) and specificity 93.8% (95% CI 89.1% to 96.6%) (23 studies, 6546 participants; very low-certainty evidence). - CEUS for resectable hepatocellular carcinoma: sensitivity 77.5% (95% CI 62.9% to 87.6%) and specificity 92.7% (95% CI 86.8% to 96.1%) (13 studies, 1257 participants; low-certainty evidence). The observed heterogeneity in the results remains unexplained. The sensitivity analyses, including only studies with clearly prespecified positivity criteria and only studies in which the reference standard results were interpreted with no knowledge of the results about the index test, showed no differences in the results.

AUTHORS' CONCLUSIONS

We found that by using CEUS, as an add-on test following abdominal ultrasound, to diagnose hepatocellular carcinoma of any size and stage, 22% of people with hepatocellular carcinoma would be missed, and 6% of people without hepatocellular carcinoma would unnecessarily undergo further testing or inappropriate treatment. As to resectable hepatocellular carcinoma, we found that 23% of people with resectable hepatocellular carcinoma would incorrectly be unresected, while 8% of people without hepatocellular carcinoma would undergo further inappropriate testing or treatment. The uncertainty resulting from the high risk of bias of the included studies, heterogeneity, and imprecision of the results and concerns on their applicability limit our ability to draw confident conclusions.

Deep Learning of Liver Contrast-Enhanced Ultrasound to Predict Microvascular Invasion and Prognosis in Hepatocellular Carcinoma

Background and Aims

Microvascular invasion (MVI) is a well-known risk factor for poor prognosis in hepatocellular carcinoma (HCC). This study aimed to develop a deep convolutional neural network (DCNN) model based on contrast-enhanced ultrasound (CEUS) to predict MVI, and thus to predict prognosis in patients with HCC.

Methods

A total of 436 patients with surgically resected HCC who underwent preoperative CEUS were retrospectively enrolled. Patients were divided into training (n = 301), validation (n = 102), and test (n = 33) sets. A clinical model (Clinical model), a CEUS video-based DCNN model (CEUS-DCNN model), and a fusion model based on CEUS video and clinical variables (CECL-DCNN model) were built to predict MVI. Survival analysis was used to evaluate the clinical performance of the predicted MVI.

Results

Compared with the Clinical model, the CEUS-DCNN model exhibited similar sensitivity, but higher specificity (71.4% vs. 38.1%, p = 0.03) in the test group. The CECL-DCNN model showed significantly higher specificity (81.0% vs. 38.1%, p = 0.005) and accuracy (78.8% vs. 51.5%, p = 0.009) than the Clinical model, with an AUC of 0.865. The Clinical predicted MVI could not significantly distinguish OS or RFS (both p > 0.05), while the CEUS-DCNN predicted MVI could only predict the earlier recurrence (hazard ratio [HR] with 95% confidence interval [CI 2.92 [1.1–7.75], p = 0.024). However, the CECL-DCNN predicted MVI was a significant prognostic factor for both OS (HR with 95% CI: 6.03 [1.7–21.39], p = 0.009) and RFS (HR with 95% CI: 3.3 [1.23–8.91], p = 0.011) in the test group.

Conclusions

The proposed CECL-DCNN model based on preoperative CEUS video can serve as a noninvasive tool to predict MVI status in HCC, thereby predicting poor prognosis.

Diagnostic Performance of LI-RADS Version 2018 for Primary Liver Cancer in Patients With Liver Cirrhosis on Enhanced MRI

Purpose

The study evaluated the diagnostic performance of the Liver Imaging Reporting and Data System (LI-RADS) version 2018 for differentiating hepatocellular carcinoma (HCC) from primary liver cancer in patients with liver cirrhosis based on the updated 2019 WHO classification.

Materials and Methods

From 2016 to 2021, 300 patients with surgically confirmed primary liver cancer (PLC) and liver cirrhosis based on the updated 2019 WHO classification were eligible for this retrospective study (100 cases in each of three groups including HCC, ICC, and cHCC-CCA). Two radiologists were blinded to the final diagnosis and independently assigned an LI-RADS category to each liver nodule. The diagnostic performances of the LR-5 category (definitely HCC), and the LR-M category (probably or definitely malignant, but not specific for HCC) were calculated in overall and small observations (<20 mm). Comparisons between groups of categorical variables were performed by one-way analysis of variance and the Chi-squared or Fisher’s exact test.

Results

The mean age of 300 patients (226 men and 74 women) was 57.40 ± 11.05 years. The sensitivity and specificity of the LR-5 category for differentiating HCCs from other primary liver cancers were 81% (81 of 100) and 82% (164 of 200), respectively. The LR-M category had a sensitivity of 63% (126 of 200) for diagnosing non-HCCs (ICCs and cHCC-CCAs), with a specificity of 90% (90 of 100). The LR-5 category had a sensitivity of 82.5% (33 of 40) for diagnosing HCCs in small observations (<20 mm) with a specificity of 76.6% (59 of 77). On the contrary, LR-M demonstrated slightly higher specificity (93.8%) and sensitivity (73.8%) for diagnosing non-HCCs with tumor size <20 mm.

Conclusion

The LR-5 category as well as the LR-M category of Liver Imaging Reporting and Data System (LI-RADS) version 2018 can effectively distinguish hepatocellular carcinoma from other primary hepatic malignancies in patients with liver cirrhosis, especially for small observations (<20 mm).

Radiomics for the detection of microvascular invasion in hepatocellular carcinoma

Hepatocellular carcinoma (HCC) is the most common primary liver cancer, accounting for about 90% of liver cancer cases. It is currently the fifth most common cancer in the world and the third leading cause of cancer-related mortality. Moreover, recurrence of HCC is common. Microvascular invasion (MVI) is a major factor associated with recurrence in postoperative HCC. It is difficult to evaluate MVI using traditional imaging modalities. Currently, MVI is assessed primarily through pathological and immunohistochemical analyses of postoperative tissue samples. Needle biopsy is the primary method used to confirm MVI diagnosis before surgery. As the puncture specimens represent just a small part of the tumor, and given the heterogeneity of HCC, biopsy samples may yield false-negative results. Radiomics, an emerging, powerful, and non-invasive tool based on various imaging modalities, such as computed tomography, magnetic resonance imaging, ultrasound, and positron emission tomography, can predict the HCC-MVI status preoperatively by delineating the tumor and/or the regions at a certain distance from the surface of the tumor to extract the image features. Although positive results have been reported for radiomics, its drawbacks have limited its clinical translation. This article reviews the application of radiomics, based on various imaging modalities, in preoperative evaluation of HCC-MVI and explores future research directions that facilitate its clinical translation.

Diagnostic accuracy of contrast-enhanced ultrasound for microvascular invasion of hepatocellular carcinoma: A protocol for systematic review and meta-analysis

BACKGROUND

Microvascular invasion is an independent risk factor for the recurrence of hepatocellular carcinoma (HCC). Early detection and timely treatment can reduce the recurrence and prolong the overall survival of HCC. Contrast-enhanced ultrasound (CEUS) has been validated for their predictive potential of microvascular invasion in HCC patients, although the conclusion remains controversial. Therefore, a meta-analysis is necessary to be conducted to validate the diagnostic value of CEUS for microvascular invasion in HCC, thus supporting guideline development and clinical practice.

METHODS

Relevant studies reporting the potential diagnostic value of CEUS for microvascular invasion in HCC patients published before February 2022 will be searched in the PubMed, EMBASE, Cochrane Library, and Web of Science. Data will be extracted by 2 researchers independently. The risk of bias will be assessed by the Quality Assessment of Diagnostic Accuracy Studies-2. All of the above statistical analysis will be carried out with Stata 14.0.

RESULTS

The results of this study will be published in a peer-reviewed journal.

CONCLUSION

This study will comprehensively evaluate the diagnostic accuracy of CEUS for microvascular invasion in HCC patients, thus providing high-quality evidence to support clinical practice and guideline development.

Radiomics Models for Predicting Microvascular Invasion in Hepatocellular Carcinoma: A Systematic Review and Radiomics Quality Score Assessment

Preoperative prediction of microvascular invasion (MVI) is of importance in hepatocellular carcinoma (HCC) patient treatment management. Plenty of radiomics models for MVI prediction have been proposed. This study aimed to elucidate the role of radiomics models in the prediction of MVI and to evaluate their methodological quality. The methodological quality was assessed by the Radiomics Quality Score (RQS), and the risk of bias was evaluated by the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2). Twenty-two studies using CT, MRI, or PET/CT for MVI prediction were included. All were retrospective studies, and only two had an external validation cohort. The AUC values of the prediction models ranged from 0.69 to 0.94 in the test cohort. Substantial methodological heterogeneity existed, and the methodological quality was low, with an average RQS score of 10 (28% of the total). Most studies demonstrated a low or unclear risk of bias in the domains of QUADAS-2. In conclusion, a radiomics model could be an accurate and effective tool for MVI prediction in HCC patients, although the methodological quality has so far been insufficient. Future prospective studies with an external validation cohort in accordance with a standardized radiomics workflow are expected to supply a reliable model that translates into clinical utilization.

Radiomics Models for Predicting Microvascular Invasion in Hepatocellular Carcinoma: A Systematic Review and Radiomics Quality Score Assessment

Preoperative prediction of microvascular invasion (MVI) is of importance in hepatocellular carcinoma (HCC) patient treatment management. Plenty of radiomics models for MVI prediction have been proposed. This study aimed to elucidate the role of radiomics models in the prediction of MVI and to evaluate their methodological quality. The methodological quality was assessed by the Radiomics Quality Score (RQS), and the risk of bias was evaluated by the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2). Twenty-two studies using CT, MRI, or PET/CT for MVI prediction were included. All were retrospective studies, and only two had an external validation cohort. The AUC values of the prediction models ranged from 0.69 to 0.94 in the test cohort. Substantial methodological heterogeneity existed, and the methodological quality was low, with an average RQS score of 10 (28% of the total). Most studies demonstrated a low or unclear risk of bias in the domains of QUADAS-2. In conclusion, a radiomics model could be an accurate and effective tool for MVI prediction in HCC patients, although the methodological quality has so far been insufficient. Future prospective studies with an external validation cohort in accordance with a standardized radiomics workflow are expected to supply a reliable model that translates into clinical utilization.