Preoperative prediction of hepatocellular carcinoma tumour grade and micro-vascular invasion by means of artificial neural network: A pilot study

Cucchetti, Alessandro; Piscaglia, Fabio; Grigioni, Antonia DʼErrico; Ravaioli, Matteo; Cescon, Matteo; Zanello, Matteo; Grazi, Gian Luca; Golfieri, Rita; Grigioni, W.; Pinna, Antonio Daniele

doi:10.1016/j.jhep.2009.12.037

Cited by 168 publications

(143 citation statements)

References 41 publications

Supporting

Mentioning

134

Contrasting

Order By: Relevance

“…A radiomics nomogram to predict microvascular invasion risk in HBV-related HCC • 125 In the present study, presence of nonsmooth tumor margins, hypoattenuating halos, and internal arteries was significantly associated with MVI status in the training and validation cohorts, which is in agreement with the results of previous studies (29)(30)(31)(32). A previous study reported radiogenomic venous invasion (RVI), which included internal arteries, hypodense halo, and tumor-liver difference, as a contrast-enhanced CT biomarker for prediction of MVI (13).…”

Section: Discussionsupporting

confidence: 91%

A radiomics nomogram for preoperative prediction of microvascular invasion risk in hepatitis B virus-related hepatocellular carcinoma

Peng

Zhang

et al. 2018

Diagn Interv Radiol

159

124

View full text Add to dashboard Cite

H epatocellular carcinoma (HCC) is the sixth most common type of cancer and ranks third as a cause of cancer-related death globally. Worldwide, approximately 630 000 new cases of HCC occur annually, with more than half of these cases occurring in China (1). This disease is related to hepatitis B virus (HBV) infection in almost 70%-90% of cases in the highly endemic Asia-Pacific regions, especially in China (2, 3). Partial hepatectomy and liver transplantation are the most effective curative treatments, albeit in a limited number of cases (4). Indeed, the 5-year recurrence rates after surgical treatment and liver transplantation are as high as 70% and 35%, respectively (5-7). It is, therefore, necessary to find effective biomarkers that can identify aggressive behavior and predict tumor recurrence after liver resection and transplantation.In HCC, the presence of microvascular invasion (MVI) is a histopathologic feature indicative of aggressive behavior (8). Previous studies have identified MVI as a major risk factor for early recurrence in the first two years after liver resection and transplantation (9). Precise identification of MVI involvement in patients with HCC is critical to develop treatment strategies and arrive at prognoses. Over the past decade, researchers have made persistent endeavors towards the preoperative prediction of MVI (10-12). Although several radiologic features on contrast-enhanced magnetic resonance imaging (MRI) and computed tomography (CT) images (such as tumor margin, internal arteries, and hypodense halos) are known PURPOSE We aimed to develop and validate a radiomics nomogram for preoperative prediction of microvascular invasion (MVI) in hepatitis B virus (HBV)-related hepatocellular carcinoma (HCC). METHODSA total of 304 eligible patients with HCC were randomly divided into training (n=184) and independent validation (n=120) cohorts. Portal venous and arterial phase computed tomography data of the HCCs were collected to extract radiomic features. Using the least absolute shrinkage and selection operator algorithm, the training set was processed to reduce data dimensions, feature selection, and construction of a radiomics signature. Then, a prediction model including the radiomics signature, radiologic features, and alpha-fetoprotein (AFP) level, as presented in a radiomics nomogram, was developed using multivariable logistic regression analysis. The radiomics nomogram was analyzed based on its discrimination ability, calibration, and clinical usefulness. Internal cohort data were validated using the radiomics nomogram. RESULTSThe radiomics signature was significantly associated with MVI status (P < 0.001, both cohorts). Predictors, including the radiomics signature, nonsmooth tumor margin, hypoattenuating halos, internal arteries, and alpha-fetoprotein level were reserved in the individualized prediction no- CONCLUSIONThe radiomics nomogram, as a noninvasive preoperative prediction method, shows a favorable predictive accuracy for MVI status in patients with HBV-related HCC.

show abstract

Section: Discussionsupporting

confidence: 91%

A radiomics nomogram for preoperative prediction of microvascular invasion risk in hepatitis B virus-related hepatocellular carcinoma

Peng

Zhang

et al. 2018

Diagn Interv Radiol

159

124

View full text Add to dashboard Cite

show abstract

“…This phenomenon was also observed in the current analysis. It has indeed been reported that the larger the tumor, the poorer the differentiation grade, and the higher the incidence of mVi [23]. Both variables are connected with a higher risk of recurrent HCC [24,25].…”

Section: Discussionmentioning

confidence: 93%

Recurrence of hepatocellular cancer after liver transplantation: The role of primary resection and salvage transplantation in East and West

Lai¹,

Avolio²,

Lerut³

et al. 2012

Journal of Hepatology

View full text Add to dashboard Cite

“…However, microvascular invasion resulting from HCC is difficult to detect on preoperative imaging. Although invasion of major branches of the portal or hepatic vein can be accurately identified with sensitivities of 81%-95% on preoperative imaging (9,15), it is still difficult to detect microvascular invasion caused by HCC (16).…”

mentioning

confidence: 99%

Prediction of microvascular invasion of hepatocellular carcinoma: Usefulness of peritumoral hypointensity seen on gadoxetate disodium‐enhanced hepatobiliary phase images

Kim

Jeon

et al. 2011

Magnetic Resonance Imaging

165

150

View full text Add to dashboard Cite

Purpose: To determine whether peritumoral hypointensity seen on hepatobiliary phase images of preoperative gadoxetate disodium-enhanced magnetic resonance imaging (EOB-MRI) is useful for predicting microvascular invasion of hepatocellular carcinoma (HCC). Materials and Methods:This study was approved by the Institutional Review Board. In all, 104 HCC masses in 104 patients who had undergone EOB-MRI and liver surgery within 1 month after EOB-MRI were evaluated. Two radiologists independently recorded the presence of a peritumoral hypointensity on hepatobiliary phase. Interobserver agreement was assessed and consensus records were used. Tumor size was measured. A chi-square test and independent t-test were used for univariate analysis. Multiple logistic regression was performed to determine factors for predicting microvascular invasion. Sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of peritumoral hypointensity were calculated.Results: Sixty HCCs had microvascular invasion and 44 did not. Interobserver agreement in determining peritumoral hypointensity was excellent (k ¼ 0.83). By univariate analysis, peritumoral hypointensity and tumor size were significant for predicting microvascular invasion of HCC. On multiple logistic regression analysis, only peritumoral hypointensity was significant in predicting microvascular invasion of HCC (P ¼ 0.013). The sensitivity, specificity, PPV, and NPV of peritumoral hypointensity were 38.3%, 93.2%, 88.5%, and 52.6%, respectively. Conclusion:Peritumoral hypointensity on the hepatobiliary phase of EOB-MRI is not sensitive but has high specificity for predicting microvascular invasion of HCC.

show abstract

Preoperative prediction of hepatocellular carcinoma tumour grade and micro-vascular invasion by means of artificial neural network: A pilot study

Cited by 168 publications

References 41 publications

A radiomics nomogram for preoperative prediction of microvascular invasion risk in hepatitis B virus-related hepatocellular carcinoma

A radiomics nomogram for preoperative prediction of microvascular invasion risk in hepatitis B virus-related hepatocellular carcinoma

Recurrence of hepatocellular cancer after liver transplantation: The role of primary resection and salvage transplantation in East and West

Prediction of microvascular invasion of hepatocellular carcinoma: Usefulness of peritumoral hypointensity seen on gadoxetate disodium‐enhanced hepatobiliary phase images

Contact Info

Product

Resources

About