Application of a Convolutional Neural Network for Multitask Learning to Simultaneously Predict Microvascular Invasion and Vessels that Encapsulate Tumor Clusters in Hepatocellular Carcinoma

Diagnostics and omics technologies for the detection and prediction of metabolic dysfunction-associated steatotic liver disease-related malignancies

The prevalence of metabolic dysfunction-associated steatotic liver disease (MASLD) continues to rise, making it the leading etiology of chronic liver diseases and a prime cause of liver-related mortality. MASLD can progress into steatohepatitis (termed MASH), fibrosis, cirrhosis, and ultimately cancer. MASLD is associated with increased risks of hepatocellular carcinoma (HCC) and also extrahepatic malignancies, which can develop in both cirrhotic and non-cirrhotic patients, emphasizing the importance of identifying patients with MASLD at risk of developing MASLD-associated malignancies. However, the optimal screening, diagnostic, and risk stratification strategies for patients with MASLD at risk of cancer are still under debate. Individuals with MASH-associated cirrhosis are recommended to undergo surveillance for HCC (e.g. by ultrasound and biomarkers) every six months. No specific screening approaches for MASLD-related malignancies in non-cirrhotic cases are established to date. The rapidly developing omics technologies, including genetics, metabolomics, and proteomics, show great potential for discovering non-invasive markers to fulfill this unmet need. This review provides an overview on the incidence and mortality of MASLD-associated malignancies, current strategies for HCC screening, surveillance and diagnosis in patients with MASLD, and the evolving role of omics technologies in the discovery of non-invasive markers for the prediction and risk stratification of MASLD-associated HCC.

Radiomics analysis of gadoxetic acid-enhanced MRI for evaluating vessels encapsulating tumour clusters in hepatocellular carcinoma

Purpose

The aim of this study was to develop an integrated model that combines clinical-radiologic and radiomics features based on gadoxetic acid-enhanced MRI for preoperative evaluating of vessels encapsulating tumour clusters (VETC) patterns in hepatocellular carcinoma (HCC).

Methods

This retrospective study encompassed 234 patients who underwent surgical resection. Among them, 101 patients exhibited VETC-positive HCC, while 133 patients displayed VETC-negative HCC. Volumes of interest were manually delineated for entire tumour regions in the arterial phase (AP), portal phase (PP), and hepatobiliary phase (HBP) images. Independent predictors for VETC were identified through least absolute shrinkage and selection operator (LASSO) regression and multivariable logistic regression analysis, utilising radiomics-AP, PP, HBP, along with 24 imaging features and 19 clinical characteristics. Subsequently, the clinico-radiologic model, radiomics model, and integrated model were established, with a nomogram visualising the integrated model. The performance for VETC prediction was evaluated using a receiver operating characteristic curve.

Results

The integrated model, composed of 3 selected traditional imaging features (necrosis or severe ischemia [OR=2.457], peripheral washout [OR=1.678], LLR_AP (Lesion to liver ratio_AP) [OR=0.433] and radiomics-AP [OR=2.870], radiomics-HBP [OR=2.023], radiomics-PP [OR=1.546]), showcased good accuracy in predicting VETC patterns in both the training (AUC=0.873, 95% confidence interval [CI]: 0.821-0.925)) and validation (AUC=0.869, 95% CI:0.789-0.950) cohorts.

Conclusion

This study established an integrated model that combines traditional imaging features and radiomic features from gadoxetic acid-enhanced MRI, demonstrating good performance in predicting VETC patterns.

A nomogram for preoperative prediction of vessels encapsulating tumor clusters (VETC) pattern and prognosis of hepatocellular carcinoma

BACKGROUND

Vessels encapsulating tumor clusters (VETC) pattern of hepatocellular carcinoma (HCC) are associated with unfavorable prognosis. This study aimed to establish a nomogram model to predict VETC patterns based on preoperative CT imaging features.

PATIENTS AND METHODS

Patients who underwent surgical resection between January 1, 2016 and August 31, 2022 were retrospectively included. Predictors associated with VETC pattern were determined by using logistic regression analyses, and a nomogram model was constructed. Prognostic factors associated with recurrence-free survival (RFS) after surgical resection were identified by using Cox regression analyses.

RESULTS

A total of 84 patients were included for CT analysis. All patients underwent radical surgical resection. AST/ALT >1.07(odds ratio [OR], 4.91; 95 ​% CI: 1.11, 21.68; P ​< ​0.05), intratumoral necrosis (OR, 4.99; 95 ​% CI: 1.25, 19.99; P ​< ​0.05) and enhancing capsule (OR, 3.32; 95 ​% CI: 1.27, 8.94; P ​< ​0.05) were independent predictors of VETC pattern. These features were used for the construction of nomogram model, which showed comparable prediction performance, with AUC value of 0.767 (95%CI [0.662, 0.852]). CK19 status (Hazard ratio [HR], 2.02; 95 ​% CI: 1.06, 3.86; P ​< ​0.05), the number of tumors (HR, 3.31; 95 ​% CI: 1.47, 7.45; P ​< ​0.05) and VETC pattern (HR, 2.52; 95 ​% CI: 1.31, 4.86; P ​< ​0.05) were independent predictors of postoperative RFS.

CONCLUSION

A nomogram model based on preoperative CT imaging features could be used for the characterization of VETC pattern, and has prognostic significance for postoperative RFS in patients with HCC.

The prognostic value of vessels encapsulating tumor clusters (VETC) in patients with hepatocellular carcinoma: a systematic review and meta-analysis

BACKGROUND

Studies have suggested that vessels encapsulating tumor clusters (VETC) is a strong predictor of prognosis in patients with hepatocellular carcinoma (HCC).

METHODS

A systematic search was conducted in PubMed, Embase, Web of Science, and Scopus databases. Overall survival (OS) and tumor efficacy (TE) were two outcome measures used to evaluate the relationship between VETC and HCC prognosis. Hazard ratios (HR) and their 95% confidence intervals (CI) were used.

RESULTS

Thirteen studies with 4429 patients were included in the meta-analysis. The results showed that VETC was significantly associated with both OS (HR 2.00; 95% CI 1.64-2.45) and TE (HR 1.70; 95% CI 1.44-1.99) in HCC patients. Furthermore, recurrence-free survival (RFS) was a stronger indicator of tumor efficacy (HR 1.73; 95% CI 1.44-2.07) than disease-free survival (DFS) (HR 1.69; 95% CI 1.22-2.35). This suggests that VETC-positive HCC has a higher risk of recurrence and a lower survival rate.

CONCLUSION

In conclusion, the meta-analysis suggests that VETC is a significant predictor of overall survival and tumor efficacy in HCC patients and may be a valid prognostic indicator.

Deep learning model based on contrast-enhanced ultrasound for predicting vessels encapsulating tumor clusters in hepatocellular carcinoma

OBJECTIVES

To establish and validate a non-invasive deep learning (DL) model based on contrast-enhanced ultrasound (CEUS) to predict vessels encapsulating tumor clusters (VETC) patterns in hepatocellular carcinoma (HCC).

MATERIALS AND METHODS

This retrospective study included consecutive HCC patients with preoperative CEUS images and available tissue specimens. Patients were randomly allocated into the training and test cohorts. CEUS images were analyzed using the ResNet-18 convolutional neural network for the development and validation of the VETC predictive model. The predictive value for postoperative early recurrence (ER) of the proposed model was further evaluated.

RESULTS

A total of 242 patients were enrolled finally, including 195 in the training cohort (54.6 ± 11.2 years, 178 males) and 47 in the test cohort (55.1 ± 10.6 years, 40 males). The DL model (DL signature) achieved favorable performance in both the training cohort (area under the receiver operating characteristics curve [AUC]: 0.92, 95% confidence interval [CI]: 0.88-0.96) and test cohort (AUC: 0.90, 95% CI: 0.82-0.99). The stratified analysis demonstrated good discrimination of DL signature regardless of tumor size. Moreover, the DL signature was found independently correlated with postoperative ER (hazard ratio [HR]: 1.99, 95% CI: 1.29-3.06, p = 0.002). C-indexes of 0.70 and 0.73 were achieved when the DL signature was used to predict ER independently and combined with clinical features.

CONCLUSION

The proposed DL signature provides a non-invasive and practical method for VETC-HCC prediction, and contributes to the identification of patients with high risk of postoperative ER.

CLINICAL RELEVANCE STATEMENT

This DL model based on contrast-enhanced US displayed an important role in non-invasive diagnosis and prognostication for patients with VETC-HCC, which was helpful in individualized management.

KEY POINTS

Preoperative biopsy to determine VETC status in HCC patients is limited. The contrast-enhanced DL model provides a non-invasive tool for the prediction of VETC-HCC. The proposed deep-learning signature assisted in identifying patients with a high risk of postoperative ER.

Radiomics Model of Dynamic Contrast-Enhanced MRI for Evaluating Vessels Encapsulating Tumor Clusters and Microvascular Invasion in Hepatocellular Carcinoma

RATIONALE AND OBJECTIVES

To develop and validate a clinical-radiomics model of dynamic contrast-enhanced MRI (DCE-MRI) for the preoperative discrimination of Vessels encapsulating tumor clusters (VETC)- microvascular invasion (MVI) and prognosis of hepatocellular carcinoma (HCC).

MATERIALS AND METHODS

219 HCC patients from Institution 1 were split into internal training and validation groups, with 101 patients from Institution 2 assigned to external validation. Histologically confirmed VETC-MVI pattern categorizing HCC into VM-HCC+ (VETC+/MVI+, VETC-/MVI+, VETC+/MVI-) and VM-HCC- (VETC-/MVI-). The regions of intratumor and peritumor were segmented manually in the arterial, portal-venous and delayed phase (AP, PP, and DP, respectively) of DCE-MRI. Six radiomics models (intratumor and peritumor in AP, PP, and DP of DCE-MRI) and one clinical model were developed for assessing VM-HCC. Establishing intra-tumoral and peri-tumoral models through combining intratumor and peritumor features. The best-performing radiomics model and the clinical model were then integrated to create a Combined model.

RESULTS

In institution 1, pathological VM-HCC+ were confirmed in 88 patients (training set: 61, validation set: 27). In internal testing, the Combined model had an AUC of 0.85 (95% CI: 0.76-0.93), which reached an AUC of 0.75 (95% CI: 0.66-0.85) in external validation. The model's predictions were associated with early recurrence and progression-free survival in HCC patients.

CONCLUSIONS

The clinical-radiomics model offers a non-invasive approach to discern VM-HCC and predict HCC patients' prognosis preoperatively, which could offer clinicians valuable insights during the decision-making phase.

Magnetic Resonance Deep Learning Radiomic Model Based on Distinct Metastatic Vascular Patterns for Evaluating Recurrence-Free Survival in Hepatocellular Carcinoma

BACKGROUND

The metastatic vascular patterns of hepatocellular carcinoma (HCC) are mainly microvascular invasion (MVI) and vessels encapsulating tumor clusters (VETC). However, most existing VETC-related radiological studies still focus on the prediction of VETC status.

PURPOSE

This study aimed to build and compare VETC-MVI related models (clinical, radiomics, and deep learning) associated with recurrence-free survival of HCC patients.

STUDY TYPE

Retrospective.

POPULATION

398 HCC patients (349 male, 49 female; median age 51.7 years, and age range: 22-80 years) who underwent resection from five hospitals in China. The patients were randomly divided into training cohort (n = 358) and test cohort (n = 40).

FIELD STRENGTH/SEQUENCE

3-T, pre-contrast T1-weighted imaging spoiled gradient recalled echo (T1WI SPGR), T2-weighted imaging fast spin echo (T2WI FSE), and contrast enhanced arterial phase (AP), delay phase (DP).

ASSESSMENT

Two radiologists performed the segmentation of HCC on T1WI, T2WI, AP, and DP images, from which radiomic features were extracted. The RFS related clinical characteristics (VETC, MVI, Barcelona stage, tumor maximum diameter, and alpha fetoprotein) and radiomic features were used to build the clinical model, clinical-radiomic (CR) nomogram, deep learning model. The follow-up process was done 1 month after resection, and every 3 months subsequently. The RFS was defined as the date of resection to the date of recurrence confirmed by radiology or the last follow-up. Patients were followed up until December 31, 2022.

STATISTICAL TESTS

Univariate COX regression, least absolute shrinkage and selection operator (LASSO), Kaplan-Meier curves, log-rank test, C-index, and area under the curve (AUC). P < 0.05 was considered statistically significant.

RESULTS

The C-index of deep learning model achieved 0.830 in test cohort compared with CR nomogram (0.731), radiomic signature (0.707), and clinical model (0.702). The average RFS of the overall patients was 26.77 months (range 1-80 months).

DATA CONCLUSION

MR deep learning model based on VETC and MVI provides a potential tool for survival assessment.

EVIDENCE LEVEL

3 TECHNICAL EFFICACY: Stage 3.

Multitask deep learning for prediction of microvascular invasion and recurrence-free survival in hepatocellular carcinoma based on MRI images

BACKGROUND AND AIMS

Accurate preoperative prediction of microvascular invasion (MVI) and recurrence-free survival (RFS) is vital for personalised hepatocellular carcinoma (HCC) management. We developed a multitask deep learning model to predict MVI and RFS using preoperative MRI scans.

METHODS

Utilising a retrospective dataset of 725 HCC patients from seven institutions, we developed and validated a multitask deep learning model focused on predicting MVI and RFS. The model employs a transformer architecture to extract critical features from preoperative MRI scans. It was trained on a set of 234 patients and internally validated on a set of 58 patients. External validation was performed using three independent sets (n = 212, 111, 110).

RESULTS

The multitask deep learning model yielded high MVI prediction accuracy, with AUC values of 0.918 for the training set and 0.800 for the internal test set. In external test sets, AUC values were 0.837, 0.815 and 0.800. Radiologists' sensitivity and inter-rater agreement for MVI prediction improved significantly when integrated with the model. For RFS, the model achieved C-index values of 0.763 in the training set and ranged between 0.628 and 0.728 in external test sets. Notably, PA-TACE improved RFS only in patients predicted to have high MVI risk and low survival scores (p < .001).

CONCLUSIONS

Our deep learning model allows accurate MVI and survival prediction in HCC patients. Prospective studies are warranted to assess the clinical utility of this model in guiding personalised treatment in conjunction with clinical criteria.

A multi-parametric prognostic model based on clinicopathologic features: vessels encapsulating tumor clusters and hepatic plates predict overall survival in hepatocellular carcinoma patients

BACKGROUND

Vessels encapsulating tumor clusters (VETC) is a newly described vascular pattern that is distinct from microvascular invasion (MVI) in patients with hepatocellular carcinoma (HCC). Despite its importance, the current pathological diagnosis report does not include information on VETC and hepatic plates (HP). We aimed to evaluate the prognostic value of integrating VETC and HP (VETC-HP model) in the assessment of HCC.

METHODS

A total of 1255 HCC patients who underwent radical surgery were classified into training (879 patients) and validation (376 patients) cohorts. Additionally, 37 patients treated with lenvatinib were studied, included 31 patients in high-risk group and 6 patients in low-risk group. Least absolute shrinkage and selection operator (LASSO) regression analysis was used to establish a prognostic model for the training set. Harrell's concordance index (C-index), time-dependent receiver operating characteristics curve (tdROC), and decision curve analysis were utilized to evaluate our model's performance by comparing it to traditional tumor node metastasis (TNM) staging for individualized prognosis.

RESULTS

A prognostic model, VETC-HP model, based on risk scores for overall survival (OS) was established. The VETC-HP model demonstrated robust performance, with area under the curve (AUC) values of 0.832 and 0.780 for predicting 3- and 5-year OS in the training cohort, and 0.805 and 0.750 in the validation cohort, respectively. The model showed superior prediction accuracy and discrimination power compared to TNM staging, with C-index values of 0.753 and 0.672 for OS and disease-free survival (DFS) in the training cohort, and 0.728 and 0.615 in the validation cohort, respectively, compared to 0.626 and 0.573 for TNM staging in the training cohort, and 0.629 and 0.511 in the validation cohort. Thus, VETC-HP model had higher C-index than TNM stage system(p < 0.01).Furthermore, in the high-risk group, lenvatinib alone appeared to offer less clinical benefit but better disease-free survival time.

CONCLUSIONS

The VETC-HP model enhances DFS and OS prediction in HCC compared to traditional TNM staging systems. This model enables personalized temporal survival estimation, potentially improving clinical decision-making in surveillance management and treatment strategies.

Nomogram prediction of vessels encapsulating tumor clusters in small hepatocellular carcinoma ≤ 3 cm based on enhanced magnetic resonance imaging

BACKGROUND

Vessels encapsulating tumor clusters (VETC) represent a recently discovered vascular pattern associated with novel metastasis mechanisms in hepatocellular carcinoma (HCC). However, it seems that no one have focused on predicting VETC status in small HCC (sHCC). This study aimed to develop a new nomogram for predicting VETC positivity using preoperative clinical data and image features in sHCC (≤ 3 cm) patients.

AIM

To construct a nomogram that combines preoperative clinical parameters and image features to predict patterns of VETC and evaluate the prognosis of sHCC patients.

METHODS

A total of 309 patients with sHCC, who underwent segmental resection and had their VETC status confirmed, were included in the study. These patients were recruited from three different hospitals: Hospital 1 contributed 177 patients for the training set, Hospital 2 provided 78 patients for the test set, and Hospital 3 provided 54 patients for the validation set. Independent predictors of VETC were identified through univariate and multivariate logistic analyses. These independent predictors were then used to construct a VETC prediction model for sHCC. The model's performance was evaluated using the area under the curve (AUC), calibration curve, and clinical decision curve. Additionally, Kaplan-Meier survival analysis was performed to confirm whether the predicted VETC status by the model is associated with early recurrence, just as it is with the actual VETC status and early recurrence.

RESULTS

Alpha-fetoprotein_lg10, carbohydrate antigen 199, irregular shape, non-smooth margin, and arterial peritumoral enhancement were identified as independent predictors of VETC. The model incorporating these predictors demonstrated strong predictive performance. The AUC was 0.811 for the training set, 0.800 for the test set, and 0.791 for the validation set. The calibration curve indicated that the predicted probability was consistent with the actual VETC status in all three sets. Furthermore, the decision curve analysis demonstrated the clinical benefits of our model for patients with sHCC. Finally, early recurrence was more likely to occur in the VETC-positive group compared to the VETC-negative group, regardless of whether considering the actual or predicted VETC status.

CONCLUSION

Our novel prediction model demonstrates strong performance in predicting VETC positivity in sHCC (≤ 3 cm) patients, and it holds potential for predicting early recurrence. This model equips clinicians with valuable information to make informed clinical treatment decisions.

A deep learning model based on MRI for prediction of vessels encapsulating tumour clusters and prognosis in hepatocellular carcinoma

PURPOSE

This study aimed to build and evaluate a deep learning (DL) model to predict vessels encapsulating tumor clusters (VETC) and prognosis preoperatively in patients with hepatocellular carcinoma (HCC).

METHODS

320 pathologically confirmed HCC patients (58 women and 262 men) from two hospitals were included in this retrospective study. Institution 1 (n = 219) and Institution 2 (n = 101) served as the training and external test cohorts, respectively. Tumors were evaluated three-dimensionally and regions of interest were segmented manually in the arterial, portal venous, and delayed phases (AP, PP, and DP). Three ResNet-34 DL models were developed, consisting of three models based on a single sequence. The fusion model was developed by inputting the prediction probability of the output from the three single-sequence models into logistic regression. The area under the receiver operating characteristic curve (AUC) was used to compare performance, and the Delong test was used to compare AUCs. Early recurrence (ER) was defined as recurrence within two years of surgery and early recurrence-free survival (ERFS) rate was evaluated by Kaplan-Meier survival analysis.

RESULTS

Among the 320 HCC patients, 227 were VETC- and 93 were VETC+ . In the external test cohort, the fusion model showed an AUC of 0.772, a sensitivity of 0.80, and a specificity of 0.61. The fusion model-based prediction of VETC high-risk and low-risk categories exhibits a significant difference in ERFS rates, akin to the outcomes observed in VETC + and VETC- confirmed through pathological analyses (p < 0.05).

CONCLUSIONS

A DL framework based on ResNet-34 has demonstrated potential in facilitating non-invasive prediction of VETC as well as patient prognosis.

Prediction of vessels encapsulating tumor clusters pattern and prognosis of hepatocellular carcinoma based on preoperative gadolinium-ethoxybenzyl-diethylenetriaminepentaacetic acid magnetic resonance imaging

BACKGROUND

Vessels encapsulating tumor clusters (VETC) is a novel vascular pattern distinct from microvascular invasion that is significantly associated with poor prognosis in patients with hepatocellular carcinoma (HCC). This study aimed to predict the VETC pattern and prognosis of patients with HCC based on preoperative gadolinium-ethoxybenzyl-diethylenetriaminepentaacetic acid (Gd-EOB-DTPA) magnetic resonance imaging (MRI).

METHODS

Patients with HCC who underwent surgical resection and preoperative Gd-EOB-DTPA MRI between January 1, 2016 and August 31, 2022 were retrospectively included. The variables associated with VETC were evaluated using logistic regression. A nomogram model was constructed on the basis of independent risk factors. COX regression was used to determine the variables associated with recurrence-free survival (RFS).

RESULTS

A total of 98 patients with HCC were retrospectively included. Peritumoral hypointensity on the hepatobiliary phase (HBP) (odd ratio [OR], 2.58; 95% CI, 1.05-6.33; P = .04), tumor-to-liver signal intensity ratio on HBP of ≤0.75 (OR, 27.80; 95% CI, 1.53-502.91; P = .02), and tumor-to-liver apparent diffusion coefficient ratio of ≤1.23 (OR, 4.65; 95% CI, 1.01-21.38; P = .04) were independent predictors of VETC pattern. A nomogram was constructed by combining the aforementioned 3 significant variables. The accuracy, sensitivity, and specificity were 69.79%, 71.74%, and 68.00%, respectively, with an area under the receiver operating characteristic curve of 0.75 (95% CI, 0.65-0.83). The variables significantly associated with RFS of patients with HCC after surgery were Barcelona Clinic Liver Cancer stage (hazard ratio [HR], 2.15; 95% CI, 1.09-4.22; P = .03) and VETC pattern (HR, 2.28; 95% CI, 1.29-4.02; P = .004).

CONCLUSION

The preoperative imaging features based on Gd-EOB-DTPA MRI can be used to predict the VETC pattern, which has prognostic significance for postoperative RFS of patients with HCC.

MRI-Based Radiomics and Deep Learning in Biological Characteristics and Prognosis of Hepatocellular Carcinoma: Opportunities and Challenges

Hepatocellular carcinoma (HCC) is the fifth most common malignancy and the third leading cause of cancer-related death worldwide. HCC exhibits strong inter-tumor heterogeneity, with different biological characteristics closely associated with prognosis. In addition, patients with HCC often distribute at different stages and require diverse treatment options at each stage. Due to the variability in tumor sensitivity to different therapies, determining the optimal treatment approach can be challenging for clinicians prior to treatment. Artificial intelligence (AI) technology, including radiomics and deep learning approaches, has emerged as a unique opportunity to improve the spectrum of HCC clinical care by predicting biological characteristics and prognosis in the medical imaging field. The radiomics approach utilizes handcrafted features derived from specific mathematical formulas to construct various machine-learning models for medical applications. In terms of the deep learning approach, convolutional neural network models are developed to achieve high classification performance based on automatic feature extraction from images. Magnetic resonance imaging offers the advantage of superior tissue resolution and functional information. This comprehensive evaluation plays a vital role in the accurate assessment and effective treatment planning for HCC patients. Recent studies have applied radiomics and deep learning approaches to develop AI-enabled models to improve accuracy in predicting biological characteristics and prognosis, such as microvascular invasion and tumor recurrence. Although AI-enabled models have demonstrated promising potential in HCC with biological characteristics and prognosis prediction with high performance, one of the biggest challenges, interpretability, has hindered their implementation in clinical practice. In the future, continued research is needed to improve the interpretability of AI-enabled models, including aspects such as domain knowledge, novel algorithms, and multi-dimension data sources. Overcoming these challenges would allow AI-enabled models to significantly impact the care provided to HCC patients, ultimately leading to their deployment for clinical use. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY: Stage 2.

Deep Learning Radiomics Model of Dynamic Contrast-Enhanced MRI for Evaluating Vessels Encapsulating Tumor Clusters and Prognosis in Hepatocellular Carcinoma

BACKGROUND

Vessels encapsulating tumor cluster (VETC) is a critical prognostic factor and therapeutic predictor of hepatocellular carcinoma (HCC). However, noninvasive evaluation of VETC remains challenging.

PURPOSE

To develop and validate a deep learning radiomic (DLR) model of dynamic contrast-enhanced MRI (DCE-MRI) for the preoperative discrimination of VETC and prognosis of HCC.

STUDY TYPE

Retrospective.

POPULATION

A total of 221 patients with histologically confirmed HCC and stratified this cohort into training set (n = 154) and time-independent validation set (n = 67).

FIELD STRENGTH/SEQUENCE

A 1.5 T and 3.0 T; DCE imaging with T1-weighted three-dimensional fast spoiled gradient echo.

ASSESSMENT

Histological specimens were used to evaluate VETC status. VETC+ cases had a visible pattern (≥5% tumor area), while cases without any pattern were VETC-. The regions of intratumor and peritumor were segmented manually in the arterial, portal-venous and delayed phase (AP, PP, and DP, respectively) of DCE-MRI and reproducibility of segmentation was evaluated. Deep neural network and machine learning (ML) classifiers (logistic regression, decision tree, random forest, SVM, KNN, and Bayes) were used to develop nine DLR, 54 ML and clinical-radiological (CR) models based on AP, PP, and DP of DCE-MRI for evaluating VETC status and association with recurrence.

STATISTICAL TESTS

The Fleiss kappa, intraclass correlation coefficient, receiver operating characteristic curve, area under the curve (AUC), Delong test and Kaplan-Meier survival analysis. P value <0.05 was considered as statistical significance.

RESULTS

Pathological VETC+ were confirmed in 68 patients (training set: 46, validation set: 22). In the validation set, DLR model based on peritumor PP (peri-PP) phase had the best performance (AUC: 0.844) in comparison to CR (AUC: 0.591) and ML (AUC: 0.672) models. Significant differences in recurrence rates between peri-PP DLR model-predicted VETC+ and VETC- status were found.

DATA CONCLUSIONS

The DLR model provides a noninvasive method to discriminate VETC status and prognosis of HCC patients preoperatively.

EVIDENCE LEVEL

4.

TECHNICAL EFFICACY

Stage 2.

Vessels that encapsulate tumour clusters vascular pattern in hepatocellular carcinoma

Vessels that encapsulate tumour clusters (VETC) is a distinct histologic vascular pattern associated with a novel mechanism of metastasis. First described in human cancers in 2004, its prevalence and prognostic significance in hepatocellular carcinoma (HCC) has only been appreciated in the past decade with a rapidly increasing body of literature. A robust biomarker of aggressive disease, the VETC pattern is easy to recognise but relies on histologic examination of tumour tissue for its diagnosis. Radiological recognition of the VETC pattern is an area of active research and is becoming increasingly accurate. As a prognostic marker, VETC has consistently proven to be an independent predictor of disease recurrence and overall survival in patients with HCC undergoing resection and liver transplantation. It can also guide treatment by predicting response to other therapies such as transarterial chemoembolisation and sorafenib. Without prospective randomised-controlled trials or routine evaluation of VETC in clinical practice, there are currently no firm treatment recommendations for VETC-positive tumours, although some perspectives are provided in this review based on the latest knowledge of their pathogenesis - a complex interplay between tumour angiogenesis and the immune microenvironment. Nevertheless, VETC has great potential as a future biomarker that could take us one step closer to precision medicine for HCC.

A new method for predicting the microvascular invasion status of hepatocellular carcinoma through neural network analysis

AIMS

To determine the relationship between microvascular invasion (MVI) and the clinical features of hepatocellular carcinoma (HCC) and provide a method to evaluate MVI status by neutral network analysis.

METHODS

The patients were divided into two groups (MVI-positive group and MVI-negative group). Univariate analysis and multivariate logistic regression analysis were carried out to identify the independent risk factors for MVI positivity. Neural network analysis was used to analyze the different importance of the risk factors in MVI prediction.

RESULTS

We enrolled 1697 patients in this study. We found that the independent prognostic factors were age, NEU, multiple tumors, AFP level and tumor diameter. By neural network analysis, we proposed that the level of AFP was the most important risk factor for HCC in predicting MVI status (the AUC was 0.704). However, age was the most important risk factor for early-stage HCC with a single tumor (the AUC was 0.605).

CONCLUSION

Through the neutral network analysis, we could conclude that the level of AFP is the most important risk factor for MVI-positive patients and the age is the most important risk factor for early-stage HCC with a single tumor.

Radiomics: A radiological evidence-based artificial intelligence technique to facilitate personalized precision medicine in hepatocellular carcinoma

The high postoperative recurrence rates in hepatocellular carcinoma (HCC) remain a major hurdle in its management. Appropriate staging and treatment selection may alleviate the extent of fatal recurrence. However, effective methods to preoperatively evaluate pathophysiologic and molecular characteristics of HCC are lacking. Imaging plays a central role in HCC diagnosis and stratification due to the non-invasive diagnostic criteria. Vast and crucial information is hidden within image data. Other than providing a morphological sketch for lesion diagnosis, imaging could provide new insights to describe the pathophysiological and genetic landscape of HCC. Radiomics aims to facilitate diagnosis and prognosis of HCC using artificial intelligence techniques to harness the immense information contained in medical images. Radiomics produces a set of archetypal and robust imaging features that are correlated to key pathological or molecular biomarkers to preoperatively risk-stratify HCC patients. Inferred with outcome data, comprehensive combination of radiomic, clinical and/or multi-omics data could also improve direct prediction of response to treatment and prognosis. The evolution of radiomics is changing our understanding of personalized precision medicine in HCC management. Herein, we review the key techniques and clinical applications in HCC radiomics and discuss current limitations and future opportunities to improve clinical decision making.