A new horizon in risk stratification of hepatocellular carcinoma by integrating vessels that encapsulate tumor clusters and microvascular invasion

Lu, Lianghe; Wei, Wei; Huang, Chaoyun; Li, Shaohua; Zhong, Chong; Wang, Jiahong; Yu, Wu-Shen; Zhang, Yongfa; Chen, Minshan; Ling, Yihong; Guo, Rong

doi:10.1007/s12072-021-10183-w

Cited by 19 publications

(31 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The difference between the two tasks and the respective predictive abilities of the two tasks in a As two important prognostic factors, MVI and VETC are both effective in prognostic stratification. 14 Analogous results were obtained in our study. According to the difference in the MVI and VETC statuses in the results predicted by the 3D CNN, the patients were divided into four subpopulations.…”

Section: Discussionsupporting

confidence: 91%

“…Vessels encapsulating tumor clusters (VETC), affecting the recurrence-free survival (RFS) and overall survival (OS) of HCC patients, 13 is present in some patients without MVI, and these patients have a worse prognosis than those without either MVI or VETC. 14 Noting that VETC has complementary significance to MVI in predicting prognosis to some extent, recent studies began to use preoperative images to assess the VETC status. 15,16 Additionally, a significant correlation between VETC and MVI has been presented.…”

mentioning

confidence: 99%

“… 13 Lin et al 17 identified VETC and MVI as independent predictors for RFS and incorporated them into a multivariate model to predict RFS. Lu et al 14 determined the prognostic role of a novel vascular classification system based on the VETC and MVI statuses after curative resection. A certain degree of relevance exists between MVI and VETC, which could be combined as a preoperative prediction label for survival.…”

mentioning

confidence: 99%

See 2 more Smart Citations

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

et al. 2022

View full text Add to dashboard Cite

Background Hepatocellular carcinoma (HCC) is the fourth most common cause of cancer death worldwide, and the prognosis remains dismal. In this study, two pivotal factors, microvascular invasion (MVI) and vessels encapsulating tumor clusters (VETC) were preoperatively predicted simultaneously to assess prognosis. Methods A total of 133 HCC patients who underwent surgical resection and preoperative gadolinium ethoxybenzyl-diethylenetriaminepentaacetic acid (Gd-EOB-DTPA)-enhanced magnetic resonance imaging (MRI) were included. The statuses of MVI and VETC were obtained from the pathological report and CD34 immunohistochemistry, respectively. A three-dimensional convolutional neural network (3D CNN) for single-task learning aimed at MVI prediction and for multitask learning aimed at simultaneous prediction of MVI and VETC was established by using multiphase Gd-EOB-DTPA-enhanced MRI. Results The 3D CNN for single-task learning achieved an area under receiver operating characteristics curve (AUC) of 0.896 (95% CI: 0.797–0.994). Multitask learning with simultaneous extraction of MVI and VETC features improved the performance of MVI prediction, with an AUC value of 0.917 (95% CI: 0.825–1.000), and achieved an AUC value of 0.860 (95% CI: 0.728–0.993) for the VETC prediction. The multitask learning framework could stratify high- and low-risk groups regarding overall survival (p < 0.0001) and recurrence-free survival (p < 0.0001), revealing that patients with MVI+/VETC+ were associated with poor prognosis. Conclusions A deep learning framework based on 3D CNN for multitask learning to predict MVI and VETC simultaneously could improve the performance of MVI prediction while assessing the VETC status. This combined prediction can stratify prognosis and enable individualized prognostication in HCC patients before curative resection.

show abstract

Section: Discussionsupporting

confidence: 91%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

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

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In patients who underwent liver transplantation for HCC, the combination of VETC with pathologically evaluated immune status enabled further classification of patients based on their clinical outcome 4 . In the study by Lu et al, VETC status provides additional discriminative information for patients with microvascular invasion (MVI) 5 …”

Section: Introductionmentioning

confidence: 99%

The presence of vessels encapsulating tumor clusters is associated with an immunosuppressive tumor microenvironment in hepatocellular carcinoma

Zhang

Ono

Fujii

et al. 2022

Intl Journal of Cancer

View full text Add to dashboard Cite

Recently, a distinct vascular pattern in hepatocellular carcinoma (HCC) called vessels encapsulating tumor‐forming clusters (VETC) has received attention because of its association with poor prognosis. However, little is known about the mechanism by which VETC promotes an aggressive phenotype at the molecular level. In our study, the association between differences in stepwise signal intensity in the HB phase and molecular subtypes and somatic mutations associated with the immune microenvironment were investigated using the International Cancer Genome Consortium (ICGC) cohort (66 patients). To our knowledge, this is the first study to analyze the molecular patterns of VETC using RNA‐Seq data. The VETC+ HCC group showed significantly lower overall survival and higher cumulative incidence of extrahepatic metastasis after curative hepatic resection than the VETC− HCC group. The VETC+ group exhibited molecular features indicative of lower immune activation than the VETC− group, suggesting that tumor cells in the VETC+ group were more likely to escape from the immune response, which could lead to the shorter OS (Overall survival) and higher risk of metastasis. On the other hand, gene expression levels of fibroblast growth factor receptors were upregulated in VETC+ HCC, suggesting that VETC+ HCC might benefit from lenvatinib treatment. Our results demonstrate that VETC+ HCC was associated with the suppression of tumor immune responses at the molecular level.

show abstract

“…Microvascular invasion (MVI), the embolus of cancer cells with micro-metastasis in liver vessels, is an independent prognostic factor for recurrence and metastasis in HCC (3). Recently, an increasing number of studies (4,5) have shown that a precise surgical approach and timely postoperative adjuvant therapy for patients with HCC and MVI could reduce recurrence and improve survival.…”

Section: Introductionmentioning

confidence: 99%

A Promising Preoperative Prediction Model for Microvascular Invasion in Hepatocellular Carcinoma Based on an Extreme Gradient Boosting Algorithm

et al. 2022

View full text Add to dashboard Cite

BackgroundThe non-invasive preoperative diagnosis of microvascular invasion (MVI) in hepatocellular carcinoma (HCC) is vital for precise surgical decision-making and patient prognosis. Herein, we aimed to develop an MVI prediction model with valid performance and clinical interpretability.MethodsA total of 2160 patients with HCC without macroscopic invasion who underwent hepatectomy for the first time in West China Hospital from January 2015 to June 2019 were retrospectively included, and randomly divided into training and a validation cohort at a ratio of 8:2. Preoperative demographic features, imaging characteristics, and laboratory indexes of the patients were collected. Five machine learning algorithms were used: logistic regression, random forest, support vector machine, extreme gradient boosting (XGBoost), and multilayer perception. Performance was evaluated using the area under the receiver operating characteristic curve (AUC). We also determined the Shapley Additive exPlanation value to explain the influence of each feature on the MVI prediction model.ResultsThe top six important preoperative factors associated with MVI were the maximum image diameter, protein induced by vitamin K absence or antagonist-II, α-fetoprotein level, satellite nodules, alanine aminotransferase (AST)/aspartate aminotransferase (ALT) ratio, and AST level, according to the XGBoost model. The XGBoost model for preoperative prediction of MVI exhibited a better AUC (0.8, 95% confidence interval: 0.74–0.83) than the other prediction models. Furthermore, to facilitate use of the model in clinical settings, we developed a user-friendly online calculator for MVI risk prediction based on the XGBoost model.ConclusionsThe XGBoost model achieved outstanding performance for non-invasive preoperative prediction of MVI based on big data. Moreover, the MVI risk calculator would assist clinicians in conveniently determining the optimal therapeutic remedy and ameliorating the prognosis of patients with HCC.

show abstract

A new horizon in risk stratification of hepatocellular carcinoma by integrating vessels that encapsulate tumor clusters and microvascular invasion

Cited by 19 publications

References 29 publications

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

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

The presence of vessels encapsulating tumor clusters is associated with an immunosuppressive tumor microenvironment in hepatocellular carcinoma

A Promising Preoperative Prediction Model for Microvascular Invasion in Hepatocellular Carcinoma Based on an Extreme Gradient Boosting Algorithm

Contact Info

Product

Resources

About