Hepatocellular carcinoma (HCC) is characterized by high malignancy, high recurrence rate and poor prognosis. Radiofrequency ablation (RFA) is the first-line curative treatment for early-stage HCC. Yet, effective inhibition of local recurrent HCC is still challenging because of immunosuppressive tumor microenvironment (TME) and upregulation of multiple tyrosine kinase receptors in the post-RFA residual tumor. The combination of tyrosine kinase inhibitor lenvatinib and immune checkpoint blockade (ICB) therapy is a promising strategy to tackle HCC, but the limited bioavailability and weak targeting still restrict the therapeutic effect. Inspired by the predominant proinflammatory stress reaction and infiltration of macrophages in the TME of residual HCC after RFA, we developed a lenvatinib-loaded hybrid nanovesicles (PML@Len) consisting of lipid and engineered macrophage membrane overexpressing programmed cell death protein 1 (PD-1). The incorporation of macrophage membrane prevented PML@Len from being phagocytosed by kupffer cells. The replenished PD-1 not only facilitated tumor accumulation but also blocked programmed cell death ligand 1(PD-L1) overexpressed on the tumor. Additionally, delivery of lenvatinib by PML@Len resulted in effective anti-angiogenesis and regulation of immunosuppressive TME to boost anti-tumor immunity. Consequently, these hybrid nanovesicles based on engineered macrophage membrane demonstrated great potency to elicit anti-tumor memory effects of T lymphocytes, hence effectively suppressing the tumor recurrence after RFA.

Sorafenib is a commonly used first-line kinase-targeted drug for advanced hepatocellular carcinoma (HCC) patients suffering from limited efficacy. Emerging evidence indicates that sorafenib exerts anti-cancer activity through the induction of ferroptosis in HCC cells, but the underlying mechanism is still unclear.

The whole transcriptome sequencing and bioinformatics analysis were used to screen for target genes. The expression and subcellular localization of regulatory factor X1 (RFX1) were determined through immunohistochemistry, immunofluorescence, PCR and western blot analyses. The impact of RFX1 on HCC cell growth was assessed using CCK8, colony formation assays, cell death assays, and animal experiments. Glutathione measurement, iron assay and lipid peroxidation detection assays were performed to investigate ferroptosis of HCC cells. The regulatory mechanism of RFX1 in HCC was investigated by sgRFX1, co-IP, ChIP and luciferase experiments. Immunohistochemical and survival analyses were performed to examine the prognostic significance of RFX1 in HCC.

In this study, we found that RFX1 promote ferroptosis in HCC cells. Further, we showed that sorafenib induces cell death through RFX1-mediated ferroptosis in HCC cells. The enhancing effect of RFX1 on HCC cell ferroptosis is largely dependent on inhibition of cystine/glutamate antiporter (system Xc-) activity through the BECN-SLC7A11 axis, where RFX1 directly binds to the promoter region of BECN1 and upregulates BECN1 expression. In addition, a STAT3-RFX1-BECN1 signalling loop was found to promote RFX1 expression in HCC cells.

Our study reveals a novel mechanism underlying sorafenib-induced HCC cell death.

Small-molecule inhibitors of vascular endothelial growth factor receptor 2 (VEGFR2) face clinical limitations due to adverse effects. This study aimed to evaluate the novel compound SB218078 as a dual-targeting agent against both tumor angiogenesis and epithelial-mesenchymal transition (EMT) in breast cancer, while exploring its mechanisms of action.

The anti-angiogenic effects of SB218078 were investigated using in vitro models of endothelial cell migration, invasion, and tube formation, alongside in vivo zebrafish developmental angiogenesis assays. Breast cancer progression was assessed through cellular proliferation, migration, invasion tests, and mouse xenograft models. Mechanistic studies focused on the Chk1/ZEB1 signaling axis, validated through genetic interventions.

SB218078 effectively suppressed angiogenesis by inhibiting endothelial cell functions and disrupting developmental vascular networks in zebrafish. It also impeded breast cancer cell aggressiveness and tumor growth in vivo. Mechanistically, SB218078 selectively targeted ZEB1-an EMT transcription factor-via Chk1 inhibition, with ZEB1 knockdown mimicking its anti-angiogenic effects, while ZEB1 overexpression reversed this activity.

SB218078 emerges as a promising dual-action therapeutic candidate for breast cancer, simultaneously blocking angiogenesis and EMT through the Chk1-ZEB1 axis. Its specificity for ZEB1, distinct from other EMT regulators, offers a novel strategy to overcome the limitations of traditional VEGFR2 inhibitors, warranting further preclinical development.

Hepatocellular carcinoma (HCC) is a leading cause of cancer-related mortality worldwide, with an estimated 750,000 deaths in 2022. Recent emergence of molecular targeted agents and immune checkpoint inhibitors and their combination therapies have been transforming HCC care, but their prognostic impact in advanced-stage disease remains unsatisfactory. In addition, their application to early-stage disease is still an unmet need. Omics profiling studies have elucidated recurrent and heterogeneously present molecular aberrations involved in pro-cancer tumor (immune) microenvironment that may guide therapeutic strategies. Recurrent aberrations such somatic mutations in TERT promoter and TP53 have been regarded undruggable, but recent studies have suggested that these may serve as new classes of therapeutic targets. HCC markers such as alpha-fetoprotein, glypican-3, and epithelial cell adhesion molecule have also been explored as therapeutic targets. These molecular features may be utilized as biomarkers to guide the application of new approaches as companion biomarkers to maximize therapeutic benefits in patients who are likely to benefit from the therapies, while minimizing unnecessary harm in patients who will not respond. The explosive number of new agents in the pipelines have posed challenges in their clinical testing. Novel clinical trial designs guided by predictive biomarkers have been proposed to enable their efficient and cost-effective evaluation. These new developments collectively facilitate clinical translation of personalized molecular-targeted therapies in HCC and substantially improve prognosis of HCC patients.

Purpose To develop deep learning (DL) radiopathomics models based on contrast-enhanced MRI and pathologic imaging to predict vessels encapsulating tumor clusters (VETC) and survival in hepatocellular carcinoma (HCC). Materials and Methods In this retrospective, multicenter study, 578 patients with HCC (mean age [±SD], 59 years ± 10; 442 male, 136 female) were divided into the training (n = 317), internal (n = 137), and external (n = 124) test sets. DL radiomics and pathomics models were developed to predict VETC using gadoxetic acid-enhanced MR and pathologic images. Deep radiomics score (DRS) and handcrafted and deep pathomics scores were compared between the group with VETC pattern in HCC (VETC+) and group without VETC pattern in HCC (VETC-). Multivariable Cox regression analyses were performed to identify independent prognostic factors, and the radiopathomics nomogram models were developed for early recurrence and progression-free survival (PFS). The prognostic power was evaluated using the concordance index (C index) and time-dependent receiver operating characteristic (ROC) curves. Results In the external test set, the Swin Transformer showed good performance for predicting VETC in both DL radiomics (area under the ROC curve [AUC], 0.77-0.79) and pathomics (AUC, 0.79) models. Patients with VETC+ HCC had significantly higher DRS and handcrafted and deep pathomics scores compared with patients with VETC- HCC in all datasets (all P < .001). The radiopathomics nomogram model incorporating DRS in the arterial phase and the handcrafted and deep pathomics scores achieved C indexes of 0.69, 0.60, and 0.67 for early recurrence and time-dependent AUCs of 0.83 (95% CI: 0.76, 0.91), 0.81 (95% CI: 0.68, 0.94), and 0.78 (95% CI: 0.67, 0.88) for 3-year PFS in the training, internal, and external test sets, respectively. Early recurrence and PFS rates statistically significantly differed between the high- and low-risk patients stratified by the radiopathomics nomogram model (all P < .05). Conclusion DL radiopathomics models effectively helped to predict VETC in HCC and assess the risk for early recurrence and PFS. Keywords: Hepatocellular Carcinoma, Deep Learning, MRI, Radiopathomics, Survival Supplemental material is available for this article. © RSNA, 2025.

Vessels encapsulating tumor clusters (VETC) was implicated in the unfavourable prognosis of hepatocellular carcinoma (HCC). While potentially valuable for noninvasive evaluation, the proposed imaging criteria of VETC require external validation. This study aimed to evaluate the performance and prognostic value of these imaging criteria via CT and gadoxetic acid-enhanced MRI.

Retrospectively, we gathered study included 191 patients with a single HCC who underwent preoperative CT and gadoxetic acid-enhanced MRI at three tertiary care centers between January 2017 and May 2021. The performance of previously reported radiological feature-based criteria of VETC, including the SN (size and necrosis) score, the VETC nomogram, and Fan's model, were evaluated using the area under the curve (AUC) and compared using the DeLong method. Imaging estimated VETC stratification was assessed for its association with early recurrence.

Ninety-four patients (49.2%) were pathologically identified as VETC-positive HCC. No significant differences were found between CT and gadoxetic acid-enhanced MRI regarding the performance of the criteria (allP> 0.05). However, the VETC nomogram, which incorporates tumor size, necrosis, and enhancement pattern, outperformed the SN score and Fan's model (AUC: 0.825 vs. 0.716 and 0.588 at CT; 0.841 vs. 0.721 and 0.621 at gadoxetic acid-enhanced MRI, bothP< 0.001). Stratification using the VETC nomogram, validated on both CT and gadoxetic acid-enhanced MRI, was associated with early recurrence (P< 0.05).

This study confirmed that the radiological feature-based criteria of VETC in HCC are applicable to both CT and gadoxetic acid-enhanced MRI, with the VETC nomogram showing strong discriminatory power in identifying VETC-positive HCC and predicting early recurrence.

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).

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.

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.

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.

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.

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.

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).

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.

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.

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.

To establish and validate scoring models for predicting vessels encapsulating tumor clusters (VETC) in hepatocellular carcinoma (HCC) using computed tomography (CT) and magnetic resonance imaging (MRI), and to intra-individually compare the predictive performance between the two modalities.

We retrospectively included 324 patients with surgically confirmed HCC who underwent preoperative dynamic CT and MRI with extracellular contrast agent between June 2019 and August 2020. These patients were then divided into a discovery cohort (n = 227) and a validation cohort (n = 97). Imaging features and Liver Imaging Reporting and Data System (LI-RADS) categories of VETC-positive HCCs were evaluated. Logistic regression analyses were conducted on the discovery cohort to identify clinical and imaging predictors associated with VETC-positive cases. Subsequently, separate CT-based and MRI-based scoring models were developed, and their diagnostic performance was compared using generalized estimating equations.

On both CT and MRI, VETC-positive HCCs exhibited a higher frequency of size > 5.0 cm, necrosis or severe ischemia, non-smooth tumor margin, targetoid appearance, intratumor artery, and heterogeneous enhancement with septations or irregular ring-like structure compared to VETC-negative HCCs (all p < 0.05). Regarding LI-RADS categories, VETC-positive HCCs were more frequently categorized as LR-M than VETC-negative cases (all p < 0.05). In the validation cohort, the CT-based model showed similar sensitivity (76.7% vs. 86.7%, p = 0.375), specificity (83.6% vs. 74.6%, p = 0.180), and area under the curve value (0.80 vs. 0.81, p = 0.910) to the MRI-based model in predicting VETC-positive HCCs.

Preoperative CT and MRI demonstrated comparable performance in the identification of VETC-positive HCCs, thus displaying promising predictive capabilities.

Both computed tomography and magnetic resonance imaging demonstrated promise in preoperatively identifying the vessel-encapsulating tumor cluster pattern in hepatocellular carcinoma, with no statistically significant difference between the two modalities, potentially adding additional prognostic value.

Computed tomography (CT) and magnetic resonance imaging (MRI) show promise in the preoperative identification of vessels encapsulating tumor clusters-positive hepatocellular carcinoma (HCC). HCC with vessels encapsulating tumor cluster patterns were more frequently LR-M compared to those without. These CT and MRI models showed comparable ability in identifying vessels encapsulating tumor clusters-positive HCC.

Vessels encapsulating tumor clusters (VETC) pattern is tumor vasculature of HCC and is a predictor of prognosis and therapeutic efficacy. Recent radiological studies have demonstrated the predictability of VETC from preoperative images, but the mechanisms of image formation are not elucidated. This study aims to determine the relationship between VETC and intratumor heterogeneity in Gd-EOB-DTPA-enhanced magnetic resonance imaging (EOB-MRI) and to provide its pathological evidence.

Radiologists visually classified preoperative arterial- and hepatobiliary-phase EOB-MRI images of 204 surgically resected HCCs into patterns based on heterogeneity and signal intensity; these classifications were validated using texture analysis. Single and multiplex immunohistochemistry for CD34, h-caldesmon, and OATP1B3 were performed to evaluate VETC, arterial vessel density (AVD), and OATP1B3 expression. Recurrence-free survival was assessed using the generalized Wilcoxon test. The contribution of clinicoradiological factors to the prediction of VETC was evaluated by random forest and least absolute shrinkage and selection operator regression.

VETC was frequently found in tumors with arterial-phase heterogeneous hyper-enhancement patterns and in tumors with hepatobiliary-phase heterogeneous hyperintense/isointense patterns (HBP-Hetero). AVD and OATP1B3 expression positively correlated with signal intensity in the arterial and hepatobiliary phases, respectively. Intratumor spatial analysis revealed that AVD and OATP1B3 expression were lower in VETC regions than in tumor regions without VETC. Patients with HBP-Hetero tumors had shorter recurrence-free survival. Machine learning models highlighted the importance of serum PIVKA-II, tumor size, and enhancement pattern of arterial and hepatobiliary phase for VETC prediction.

VETC is associated with local reductions of both AVD and OATP1B3 expression, likely contributing to heterogeneous enhancement patterns in EOB-MRI. Evaluation of the arterial and hepatobiliary phases of EOB-MRI would enhance the predictability of VETC.

Immunotherapies have led to a paradigm shift in the treatment of hepatocellular carcinoma (HCC). Studies have revealed the single-cell catalogs of tumor-infiltrating immune cells and the trajectories of their differentiation. Nevertheless, the spatial distribution of these immune cells with distinct phenotypes in the tumor microenvironment and their clinicopathologic significance in resectable and unresectable HCCs are still largely unclear.

We analyzed the spatial dynamics of intratumoral CD4 and CD8 T cells and their association with B and plasma cells using 283 surgically resected HCC samples, 58 unresectable HCC samples before combined immunotherapy [atezolizumab plus bevacizumab (Atezo + Bev)], and autopsy specimens from 50 cases of advanced-stage HCC through multiplex IHC combined with transcriptomic and driver gene mutation analyses. Classification based on the spatial dynamics of T- and B-cell responses (refined immunosubtype) was developed, and its clinicopathologic significance was analyzed.

We found that stem-like CD4 and CD8 T cells were mainly observed in T-cell aggregates and T-cell zone of tertiary lymphoid structure (TLS). The differentiation of T follicular helper cells was associated with the development of TLS, whereas the differentiation of CXCL13-expressing CD4 TCXCL13 cells with a phenotype resembling T peripheral helper cells was associated with the development of the lymphoplasmacytic microenvironment. The refined immunosubtype could predict clinical outcomes of resectable HCC after surgery and unresectable HCC after Atezo + Bev therapy. The immune microenvironment of metastatic lesions tended to reflect those of primary lesions.

We revealed the spatial dynamics of T- and B-cell responses in HCC, which is closely associated with the clinical outcome after surgical resection or Atezo + Bev therapy.

This study aimed to establish a clinical prediction model for vessels encapsulating tumor clusters (VETC) based on preoperative ultrasonography (US) and contrast-enhanced computed tomography (CECT) imaging in patients with hepatocellular carcinoma (HCC).

Data were retrospectively collected from 215 patients who underwent hepatectomy for solitary HCC lesions. They were divided into training and validation cohorts at a ratio of 6:4. Preoperative imaging features were extracted (seven from US and nine from CECT imaging) to explore their relationship with VETC. A VETC prediction model was constructed and graphically depicted as a nomogram. Its performance was evaluated via the receiver operating characteristic (ROC) curve, the calibration curve, and decision curve analysis (DCA).

The VETC incidence for all the lesions was 37.7%. The final variables included in the nomogram were "peritumoral enhancement in CECT", "alpha-fetoprotein level > 200 ng/Ml," "halo in US," "capsule enhancement in CECT," and "posterior acoustic enhancement in US." The area under the curve (AUC) values for the training and validation cohorts were 0.824 and 0.725, respectively. The Hosmer-Lemeshow fit test showed no statistical difference (p = 0.369 and p = 0.067 for the training and validation cohorts, respectively). DCA demonstrated that our nomogram provided clinical benefits to a wide range of patients. According to the nomogram score, the VETC-positive and -negative groups demonstrated significant differences in both the training (p < 0.001) and validation (p = 0.001) cohorts.

Our prediction model based on US and CECT imaging features can accurately predict VETC in HCC.

Macrotrabecular-massive (MTM) and vessels encapsulating tumor clusters (VETC)-hepatocellular carcinoma (HCC) are aggressive histopathological phenotypes with significant prognostic implications. However, the molecular markers associated with MTM-HCC and VETC-HCC and their implications for clinical outcomes and therapeutic strategies remain unclear.

Utilizing the TCGA-LIHC cohort, we employed machine learning techniques to develop a prognostic risk score based on MTM and VETC-related genes. The performance of the risk score was assessed by investigating various aspects including clinical outcomes, biological pathways, treatment responses, drug sensitivities, tumor microenvironment, and molecular subclasses. To validate the risk score, additional data from the ICGC-JP, GSE14520, GSE104580, GSE109211, and an in-house cohort were collected and analyzed.

The machine learning algorithm established a 4-gene-based risk score. High-risk patients had significantly worse prognosis compared to low-risk patients, with the risk score being associated with malignant progression of HCC. Functionally, the high-risk group exhibited enrichment in tumor proliferation pathways. Additionally, patients in the low-risk group exhibited improved response to TACE and sorafenib treatments compared to the high-risk group. In contrast, the high-risk group exhibited reduced sensitivity to immunotherapy and increased sensitivity to paclitaxel. In the in-house cohort, high-risk patients displayed higher rates of early recurrence, along with an increased frequency of elevated alpha-fetoprotein, microvascular invasion, and aggressive MRI features associated with HCC.

This study has successfully developed a risk score based on MTM and VETC-related genes, providing a promising tool for prognosis prediction and personalized treatment strategies in HCC patients.

To explore the capability of preoperative CT imaging features, in combination with clinical indicators, for predicting vessels that encapsulate tumor clusters (VETC) pattern and prognosis in hepatocellular carcinoma (HCC).

From January 2015 to May 2022, patients with HCC who underwent curative resection and preoperative enhanced CT were retrospectively included. Clinical indicators and imaging featuresassociated with the VETC pattern were determined by logistic regression analyses. The early recurrence (ER) rate was determined using the Kaplan-Meier survival curve. Factors associated with ER after surgical resection were identified by Cox regression analyses.

A total of 243 patients with HCCwere evaluated. The total bilirubin > 17.1 μmol/L (odds ratio [OR] 3.43, 95 % Confidence Interval [CI] 1.70, 6.91, p = 0.001), serum α-fetoprotein > 100 ng/mL (OR 2.41, 95 % CI 1.25, 4.67, p = 0.009), intratumor artery (IA) (OR 2.00, 95 % CI 1.04, 3.86,p = 0.039) and arterial peritumoral enhancement (OR 2.60, 95 % CI 1.13, 5.96, p = 0.025) were independent risk factors for VETC+-HCC. The VETC+status andCT feature ofIA were associated with an increased risk of recurrence, with a shorter median RFS, compared to those without these factors (p < 0.001 and p = 0.019, respectively). In multivariable Cox regression analysis, the VETC+(hazard ratio [HR] 2.60, 95 % CI 1.66, 4.09, p < 0.001), morphological patterns of confluent multinodular growth (HR 1.79, 95 % CI 1.10, 2.91,p = 0.019), the number of the tumors (≥2) (HR 2.69, 95 % CI 1.56, 4.65, p < 0.001), and the IA (HR 1.73, 95 % CI 1.12, 2.66, p = 0.013) were independent predictors of ER in patients with HCC after surgical resection.

Preoperative CT features combined with clinical indicators could predict VETC pattern, and the CT features, along with VETC status, were of prognostic significance for early postoperative recurrence in patients with HCC.

Preoperative CT features combined with clinical indicators could predict VETC pattern, and the CT features, along with VETC status, were of prognostic significance for early recurrence in patients with HCC after surgical resection.

Vessels Encapsulating Tumor Clusters (VETC) are now recognized as independent indicators of recurrence and overall survival in hepatocellular carcinoma (HCC) patients. However, there has been limited investigation into predicting the VETC pattern using hepatobiliary phase (HBP) features from preoperative gadobenate-enhanced MRI.

This study involved 252 HCC patients with confirmed VETC status from three different hospitals (Hospital 1: training set with 142 patients; Hospital 2: test set with 64 patients; Hospital 3: validation set with 46 patients). Independent predictive factors for VETC status were determined through univariate and multivariate logistic analyses. Subsequently, these factors were used to construct two distinct VETC prediction models. Model 1 included all independent predictive factors, while Model 2 excluded HBP features. The performance of both models was assessed using the Area Under the Curve (AUC), Decision Curve Analysis, and Calibration Curve. Prediction accuracy between the two models was compared using Net Reclassification Improvement (NRI) and Integrated Discriminant Improvement (IDI).

CA199, IBIL, shape, peritumoral hyperintensity on HBP, and arterial peritumoral enhancement were independent predictors of VETC. Model 1 showed robust predictive performance, with AUCs of 0.836 (training), 0.811 (test), and 0.802 (validation). Model 2 exhibited moderate performance, with AUCs of 0.813, 0.773, and 0.783 in the respective sets. Calibration and decision curves for both models indicated consistent predictions between predicted and actual VETC, benefiting HCC patients. NRI showed Model 1 increased by 0.326, 0.389, and 0.478 in the training, test, and validation sets compared to Model 2. IDI indicated Model 1 increased by 0.036, 0.028, and 0.025 in the training, test, and validation sets compared to Model 2.

HBP features from preoperative gadobenate-enhanced MRI can enhance the predictive performance of VETC in HCC.

Hepatocellular carcinoma (HCC) progresses through multiple stages of hepatocarcinogenesis, with each stage characterized by specific changes in vascular supply, drainage, and microvascular structure. These vascular changes significantly influence the imaging findings of HCC, enabling non-invasive diagnosis. Vascular changes in HCC are closely related to aggressive histological characteristics and treatment responses. Venous drainage from the tumor toward the portal vein in the surrounding liver facilitates vascular invasion, and the unique microvascular pattern of vessels that encapsulate the tumor cluster (known as a VETC pattern) promotes vascular invasion and metastasis. Systemic treatments for HCC, which are increasingly being used, primarily target angiogenesis and immune checkpoint pathways, which are closely intertwined. By understanding the complex relationship between histopathological vascular changes in hepatocarcinogenesis and their implications for imaging findings, radiologists can enhance the accuracy of imaging diagnosis and improve the prediction of prognosis and treatment response. This, in turn, will ultimately lead to better patient care.

Vessels encapsulating tumor cluster (VETC) and microvascular invasion (MVI) have a synergistic effect on prognosis assessment and treatment selection of hepatocellular carcinoma (HCC). Preoperative noninvasive evaluation of VETC and MVI is important.

To explore the diagnosis value of preoperative gadoxetic acid (GA)-enhanced magnetic resonance imaging (MRI) features for MVI, VETC, and recurrence-free survival (RFS) in HCC.

Retrospective.

240 post-surgery patients with 274 pathologically confirmed HCC (allocated to training and validation cohorts with a 7:3 ratio) and available tumor marker data from August 2014 to December 2021.

3-T, T1-, T2-, diffusion-weighted imaging, in/out-phase imaging, and dynamic contrast-enhanced imaging.

Three radiologists subjectively reviewed preoperative MRI, evaluated clinical and conventional imaging features associated with MVI+, VETC+, and MVI+/VETC+ HCC. Regression-based nomograms were developed for HCC in the training cohort. Based on the nomograms, the RFS prognostic stratification system was further. Follow-up occurred every 3-6 months.

Chi-squared test or Fisher's exact test, Mann-Whitney U-test or t-test, least absolute shrinkage and selection operator-penalized, multivariable logistic regression analyses, receiver operating characteristic analysis, Harrell's concordance index (C-index), Kaplan-Meier plots. Significance level: P < 0.05.

In the training group, 44 patients with MVI+ and 74 patients with VETC+ were histologically confirmed. Three nomograms showed good performance in the training (C-indices: MVI+ vs. VETC+ vs. MVI+/VETC+, 0.892 vs. 0.848 vs. 0.910) and validation (C-indices: MVI+ vs. VETC+ vs. MVI+/VETC+, 0.839 vs. 0.810 vs. 0.855) cohorts. The median follow-up duration for the training cohort was 43.6 (95% CI, 35.0-52.2) months and 25.8 (95% CI, 16.1-35.6) months for the validation cohort. Patients with either pathologically confirmed or nomogram-estimated MVI, VETC, and MVI+/VETC+ suffered higher risk of recurrence.

GA-enhanced MRI and clinical variables might assist in preoperative estimation of MVI, VETC, and MVI+/VETC+ in HCC.

4 TECHNICAL EFFICACY: Stage 2.

Liver resection is one of the best treatments for small hepatocellular carcinoma (HCC), but post-resection recurrence is frequent. Biotherapies have emerged as an efficient adjuvant treatment, making the identification of patients at high risk of recurrence critical. Microvascular invasion (mVI), poor differentiation, pejorative macrotrabecular architectures, and vessels encapsulating tumor clusters architectures are the most accurate histologic predictors of recurrence, but their evaluation is time-consuming and imperfect. Herein, a supervised deep learning-based approach with ResNet34 on 680 whole slide images (WSIs) from 107 liver resection specimens was used to build an algorithm for the identification and quantification of these pejorative architectures. This model achieved an accuracy of 0.864 at patch level and 0.823 at WSI level. To assess its robustness, it was validated on an external cohort of 29 HCCs from another hospital, with an accuracy of 0.787 at WSI level, affirming its generalization capabilities. Moreover, the largest connected areas of the pejorative architectures extracted from the model were positively correlated to the presence of mVI and the number of tumor emboli. These results suggest that the identification of pejorative architectures could be an efficient surrogate of mVI and have a strong predictive value for the risk of recurrence. This study is the first step in the construction of a composite predictive algorithm for early post-resection recurrence of HCC, including artificial intelligence-based features.

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).

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.

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.

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.

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 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.

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.

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.

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

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.

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.

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.

To establish clinical prediction models of vessels encapsulating tumor clusters (VETC) pattern using preoperative contrast-enhanced ultrasound (CEUS) and gadolinium-ethoxybenzyl-diethylenetriamine pentaacetic acid magnetic resonance imaging (EOB-MRI) in patients with hepatocellular carcinoma (HCC). A total of 111 resected HCC lesions from 101 patients were included. Preoperative imaging features of CEUS and EOB-MRI, postoperative recurrence, and survival information were collected from medical records. The best subset regression and multivariable Cox regression were used to select variables to establish the prediction model. The VETC-positive group had a statistically lower survival rate than the VETC-negative group. The selected variables were peritumoral enhancement in the arterial phase (AP), hepatobiliary phase (HBP) on EOB-MRI, intratumoral branching enhancement in the AP of CEUS, intratumoral hypoenhancement in the portal phase of CEUS, incomplete capsule, and tumor size. A nomogram was developed. High and low nomogram scores with a cutoff value of 168 points showed different recurrence-free survival rates and overall survival rates. The area under the curve (AUC) and accuracy were 0.804 and 0.820, respectively, indicating good discrimination. Decision curve analysis showed a good clinical net benefit (threshold probability > 5%), while the Hosmer-Lemeshow test yielded excellent calibration (P = 0.6759). The AUC of the nomogram model combining EOB-MRI and CEUS was higher than that of the models with EOB-MRI factors only (0.767) and CEUS factors only (0.7). The nomogram verified by bootstrapping showed AUC and calibration curves similar to those of the nomogram model. The Prediction model based on CEUS and EOB-MRI is effective for preoperative noninvasive diagnosis of VETC.

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.

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

Retrospective.

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).

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).

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.

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.

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).

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

3 TECHNICAL EFFICACY: Stage 3.

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.

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.

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.

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.

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.

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

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.

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.

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.

Microvascular invasion (MVI) is a major unfavorable prognostic factor for intrahepatic metastasis and postoperative recurrence of hepatocellular carcinoma (HCC). However, the intervention and preoperative prediction for MVI remain clinical challenges due to the absent precise mechanism and molecular marker(s). Herein, we aimed to investigate the mechanisms underlying vascular invasion that can be applied to clinical intervention for MVI in HCC.

The histopathologic characteristics of clinical MVI+/HCC specimens were analyzed using multiplex immunofluorescence staining. The liver orthotopic xenograft mouse model and mechanistic experiments on human patient-derived HCC cell lines, including coculture modeling, RNA-sequencing, and proteomic analysis, were used to investigate MVI-related genes and mechanisms.

IQGAP3 overexpression was correlated significantly with MVI status and reduced survival in HCC. Upregulation of IQGAP3 promoted MVI+-HCC cells to adopt an infiltrative vessel co-optive growth pattern and accessed blood capillaries by inducing detachment of activated hepatic stellate cells (HSC) from the endothelium. Mechanically, IQGAP3 overexpression contributed to HCC vascular invasion via a dual mechanism, in which IQGAP3 induced HSC activation and disruption of the HSC-endothelial interaction via upregulation of multiple cytokines and enhanced the trans-endothelial migration of MVI+-HCC cells by remodeling the cytoskeleton by sustaining GTPase Rac1 activity. Importantly, systemic delivery of IQGAP3-targeting small-interfering RNA nanoparticles disrupted the infiltrative vessel co-optive growth pattern and reduced the MVI of HCC.

Our results revealed a plausible mechanism underlying IQGAP3-mediated microvascular invasion in HCC, and provided a potential target to develop therapeutic strategies to treat HCC with MVI.

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).

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.

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).

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

To investigate the diagnostic and prognostic value of contrast-enhanced ultrasound (CEUS) and clinical indicators of the vessels encapsulating tumor clusters (VETC) pattern and macrotrabecular-massive subtype in hepatocellular carcinoma (MTM-HCC).

This retrospective study included patients who underwent preoperative CEUS and hepatectomy for HCC between August 2018 and August 2021. Multivariable logistic regression was performed to select independent correlated factors of VETC-HCC and MTM-HCC to develop nomogram models. The association between model outcomes and early postoperative HCC recurrence was assessed using Kaplan-Meier curve and Cox regression analysis.

The training cohort included 182 patients (54.3 ± 11.3 years, 168 males) and the validation cohort included 91 patients (54.8 ± 10.6 years, 81 males). Multivariate logistic regression analysis revealed that α-fetoprotein (AFP) levels (odds ratio [OR]: 2.26, 95% confidence interval [CI]: 1.49-3.42, p < 0.001), intratumoral nonenhancement (OR: 2.40, 95% CI: 1.02-5.64, p = 0.044), and the perfusion pattern in the CEUS arterial phase (OR: 2.27, 95% CI: 1.05-4.91, p = 0.038) were independent predictors of VETC-HCC. Besides, the former two were also independently associated with MTM-HCC (AFP level: OR: 2.36, 95% CI: 1.36-4.09, p = 0.002; intratumoral nonenhancement: OR: 3.72, 95% CI: 1.02-13.56, p = 0.046). Nomogram models were constructed based on the aforementioned indicators. Kaplan-Meier curve analysis indicated that predicted VETC-HCC or MTM-HCC exhibited higher rates of early recurrence (log-rank p < 0.001 and p = 0.002, respectively). Cox regression analysis showed that a high risk of VETC-HCC was independently correlated with early recurrence (p = 0.011).

CEUS combined with AFP levels can predict VETC-HCC/MTM-HCC and prognosis preoperatively.

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).

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).

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).

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.

Recently, vessels encapsulating tumor clusters (VETC) was considered as a distinct pattern of tumor vascularization which can primarily facilitate the entry of the whole tumor cluster into the bloodstream in an invasion independent manner, and was regarded as an independent risk factor for poor prognosis in hepatocellular carcinoma (HCC).

To develop and validate a preoperative nomogram using contrast-enhanced computed tomography (CECT) to predict the presence of VETC+ in HCC.

We retrospectively evaluated 190 patients with pathologically confirmed HCC who underwent CECT scanning and immunochemical staining for cluster of differentiation 34 at two medical centers. Radiomics analysis was conducted on intratumoral and peritumoral regions in the portal vein phase. Radiomics features, essential for identifying VETC+ HCC, were extracted and utilized to develop a radiomics model using machine learning algorithms in the training set. The model's performance was validated on two separate test sets. Receiver operating characteristic (ROC) analysis was employed to compare the identified performance of three models in predicting the VETC status of HCC on both training and test sets. The most predictive model was then used to constructed a radiomics nomogram that integrated the independent clinical-radiological features. ROC and decision curve analysis were used to assess the performance characteristics of the clinical-radiological features, the radiomics features and the radiomics nomogram.

The study included 190 individuals from two independent centers, with the majority being male (81%) and a median age of 57 years (interquartile range: 51-66). The area under the curve (AUC) for the combined radiomics features selected from the intratumoral and peritumoral areas were 0.825, 0.788, and 0.680 in the training set and the two test sets. A total of 13 features were selected to construct the Rad-score. The nomogram, combining clinical-radiological and combined radiomics features could accurately predict VETC+ in all three sets, with AUC values of 0.859, 0.848 and 0.757. Decision curve analysis revealed that the radiomics nomogram was more clinically useful than both the clinical-radiological feature and the combined radiomics models.

This study demonstrates the potential utility of a CECT-based radiomics nomogram, incorporating clinical-radiological features and combined radiomics features, in the identification of VETC+ HCC.

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.

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

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.

Retrospective.

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).

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

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.

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.

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.

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

4.

Stage 2.