In hepatocellular carcinomas, any proportion of poorly differentiated components is associated with poor prognosis after hepatectomy

Computed tomography radiomics combined with clinical parameters for hepatocellular carcinoma differentiation: a machine learning investigation

Purpose

To evaluate the performance of a combined clinical-radiomics model using multiple machine learning approaches for predicting pathological differentiation in hepatocellular carcinoma (HCC).

Material and methods

A total of 196 patients with pathologically confirmed HCC, who underwent preoperative computed tomography (CT) were retrospectively enrolled (training: n = 156; validation: n = 40). The modelling process included the folowing: (1) clinical model construction through logistic regression analysis of risk factors; (2) radiomics model development by comparing 6 machine learning classifiers; and (3) integration of optimal clinical and radiomic features into a combined model. Model performance was assessed using the area under the curve (AUC), calibration curves, and decision curve analysis (DCA). A nomogram was constructed for clinical implementation.

Results

Two clinical risk factors (BMI and CA153) were identified as independent predictors of differentiated HCC. The clinical model showed moderate performance (AUC: training = 0.705, validation = 0.658). The radiomics model demonstrated improved prediction capability (AUC: training = 0.840, validation = 0.716). The combined model achieved the best performance in differentiating HCC pathological grades (AUC: training = 0.878, validation = 0.747).

Conclusions

The integration of CT radiomics features with clinical parameters through machine learning provides a promising non-invasive approach for predicting HCC pathological differentiation. This combined model could serve as a valuable tool for preoperative treatment planning.

Magnetic resonance imaging-based rim enhancement could effectually predict poor prognosis in hepatocellular carcinoma: a meta-analysis

Recent studies have initially shown that MRI-based rim enhancement associates with poor prognosis in hepatocellular carcinoma (HCC) patients, but their sample sizes are small, leading to a necessary of comprehensive analyses to make a relatively solid statement. Thus, this meta-analysis aimed to summarize the correlation between MRI-based rim enhancement and prognosis in HCC patients. Until March 2023, a literature search was conducted on Web of Science, PubMed, EMBASE, Cochrane, CNKI, Wangfang, and CQVIP databases in order to identify studies that report the correlation between MRI-based rim enhancement and the prognosis of HCC patients. MRI-based rim enhancement and prognostic data were extracted and analyzed. In our study, eight studies containing 1816 HCC patients were analyzed. Generally, the presence of MRI-based rim enhancement was related to shortened disease-free survival (DFS) [hazard ratio (HR): 2.77, 95% confidence interval (CI): 2.11-3.62, P < 0.001], and worse overall survival (OS) (HR: 5.43, 95% CI: 2.14-13.79, P < 0.001). While no other prognostic data could be retrieved. Funnel plots, Begg's test, and Egger's test all indicated that no publication bias existed; and the risk score by Newcastle-Ottawa Scale criteria ranged from 7-9 points, suggesting a generally low risk of bias. Meanwhile, the sensitivity analysis showed that the significant findings did not change by omitting each study. Then, subgroup analyses revealed that no matter stratified by tumor size, treatment option, or sample size, rim enhancement was linked with unsatisfied DFS (all P < 0.05). Conclusively, MRI-based rim enhancement could effectually estimate poor survival in HCC patients, indicating its good prognostic value.

Preoperative Evaluation of Hepatocellular Carcinoma Differentiation Using Contrast-Enhanced Ultrasound-Based Deep-Learning Radiomics Model

Objective

Distinguishing the degree of differentiation, hepatocellular carcinoma (HCC) has important clinical significance in the therapeutic decision-making and patient prognosis evaluation.

Methods

We developed a deep-learning radiomics (DLR) model based on contrast-enhanced ultrasound (CEUS) to evaluate the differentiation of HCC noninvasive. We retrospectively analyzed HCC patients who had undergone resection and CEUS one week preoperatively between November 2015 and August 2022. Enrolled patients were randomly divided into training (n=190) and testing (n=82) cohorts in a 7:3 ratio. The depth of learning and radiological characteristics reflecting the differentiation degree of HCC were extracted, and the least absolute shrinkage and selection operator(LASSO) was used for feature selection to obtain the most valuable features and then build a DLR model based on the useful features.

Results

The deep-learning Radiomics model could accurately predict the degree of differentiation of HCC; the area under the curve of the DLR model in the training and testing cohorts was 0.969 and 0.932, respectively. The accuracy, sensitivity, and specificity of the CEUS-based DLR model for predicting the differentiation of HCC were 0.915, 0.938, and 0.900, respectively, in the testing cohort. The decision curve analysis confirmed that the combined model predicted good overall net income for differentiation.

Conclusion

The CEUS-based DLR model provides an easy-to-use, visual, and personalized tool for predicting the differentiation of HCC and can help doctors formulate more favorable treatment plans for patients.

Novel postoperative nomograms for predicting individual prognoses of hepatitis B-related hepatocellular carcinoma with cirrhosis

Background

Liver cirrhosis is a well-known risk factor for carcinogenesis of hepatocellular carcinoma (HCC). The aim of the present study was to construct individual prognostic models for HCC with cirrhosis.

Methods

The clinical differences between HCC patients with and without cirrhosis were compared using a large cohort of 1003 cases. The patients with cirrhosis were randomly divided into a training cohort and a validation cohort in a ratio of 2:1. Univariate and multivariate analyses were performed to reveal the independent risk factors for recurrence-free survival (RFS) and overall survival (OS) in HCC patients with cirrhosis. These factors were subsequently used to construct nomograms.

Results

Multivariate analyses revealed that five clinical variables (hepatitis B e antigen (HBeAg) positivity, alpha-fetoprotein (AFP) level, tumour diameter, microvascular invasion (MVI), and satellite lesions) and seven variables (HBeAg positivity, AFP level, tumour diameter, MVI, satellite lesions, gamma-glutamyl transpeptidase level, and histological differentiation) were significantly associated with RFS and OS, respectively. The C-indices of the nomograms for RFS and OS were 0.739 (P < 0.001) and 0.789 (P < 0.001), respectively, in the training cohort, and 0.752 (P < 0.001) and 0.813 (P < 0.001), respectively, in the validation cohort. The C-indices of the nomograms were significantly higher than those of conventional staging systems (P < 0.001). The calibration plots showed optimal consistence between the nomogram-predicted and observed prognoses.

Conclusions

The nomograms developed in the present study showed good performance in predicting the prognoses of HCC patients with hepatitis B virus-associated cirrhosis.

Preoperative and postoperative nomograms for predicting early recurrence of hepatocellular carcinoma without macrovascular invasion after curative resection

BACKGROUND

Postoperative early recurrence (ER) is a major obstacle to long-term survival after curative liver resection (LR) in patients with hepatocellular carcinoma (HCC). This study aimed to establish preoperative and postoperative nomograms to predict ER in HCC without macrovascular invasion.

METHODS

Patients who underwent curative LR for HCC between January 2012 and December 2016 were divided into training and internal prospective validation cohorts. Nomograms were constructed based on independent risk factors derived from the multivariate logistic regression analyses in the training cohort. The predictive performances of the nomograms were validated using the internal prospective validation cohort.

RESULTS

In total, 698 patients fulfilled the eligibility criteria. Among them, 265 of 482 patients (55.0%) in the training cohort and 120 of 216 (55.6%) patients in the validation cohort developed ER. The preoperative risk factors associated with ER were age, alpha-fetoprotein, tumor diameter, and tumor number, and the postoperative risk factors associated with ER were age, tumor diameter, tumor number, microvascular invasion, and differentiation. The pre- and postoperative nomograms based on these factors showed good accuracy, with concordance indices of 0.712 and 0.850 in the training cohort, respectively, and 0.754 and 0.857 in the validation cohort, respectively. The calibration curves showed optimal agreement between the predictions by the nomograms and actual observations. The area under the receiver operating characteristic curves of the pre- and postoperative nomograms were 0.721 and 0.848 in the training cohort, respectively, and 0.754 and 0.844 in the validation cohort, respectively.

CONCLUSIONS

The nomograms constructed in this study showed good performance in predicting ER for HCC without macrovascular invasion before and after surgery. These nomograms would be helpful for doctors when determining treatments and selecting patients for regular surveillance or administration of adjuvant therapies.

Imaging Features of Main Posthepatectomy Complications: A Radiologist’s Challenge

In the recent years, the number of liver resections has seen an impressive growth. Usually, hepatic resections remain the treatment of various liver diseases, such as malignant tumors, benign tumors, hydatid disease, and abscesses. Despite technical advancements and tremendous experience in the field of liver resection of specialized centers, there are moderately high rates of postoperative morbidity and mortality, especially in high-risk and older patient populations. Although ultrasonography is usually the first-line imaging examination for postoperative complications, Computed Tomography (CT) is the imaging tool of choice in emergency settings due to its capability to assess the whole body in a few seconds and detect all possible complications. Magnetic resonance cholangiopancreatography (MRCP) is the imaging modality of choice for delineating early postoperative bile duct injuries and ischemic cholangitis that may arise in the late postoperative phase. Moreover, both MDCT and MRCP can precisely detect tumor recurrence. Consequently, radiologists should have knowledge of these surgical procedures for better comprehension of postoperative changes and recognition of the radiological features of various postoperative complications.

MRI-Based Radiomic Features Help Identify Lesions and Predict Histopathological Grade of Hepatocellular Carcinoma

Hepatocellular carcinoma (HCC) is the most common form of liver cancer. Radiomics is a promising tool that may increase the value of magnetic resonance imaging (MRI) in the management of HCC. The purpose of our study is to develop an MRI-based radiomics approach to preoperatively detect HCC and predict its histological grade. Thirty-eight HCC patients at staging who underwent axial T2-weighted and dynamic contrast-enhanced MRI (DCE-MRI) were considered. Three-dimensional volumes of interest (VOIs) were manually placed on HCC lesions and normal hepatic tissue (HT) on arterial phase post-contrast images. Radiomic features from T2 images and arterial, portal and tardive post-contrast images from DCE-MRI were extracted by using Pyradiomics. Feature selection was performed using correlation filter, Wilcoxon-rank sum test and mutual information. Predictive models were constructed for HCC differentiation with respect to HT and HCC histopathologic grading used at each step an imbalance-adjusted bootstrap resampling (IABR) on 1000 samples. Promising results were obtained from radiomic prediction models, with best AUCs ranging from 71% to 96%. Radiomics MRI based on T2 and DCE-MRI revealed promising results concerning both HCC detection and grading. It may be a suitable tool for personalized treatment of HCC patients and could also be used to develop new prognostic biomarkers useful for HCC assessment without the need for invasive procedures.

β-Catenin Expression and Its Association with Prognostic Factors in Hepatocellular Carcinoma: A Study on Alpha-fetoprotein, Histologic Grade, and Microvascular Invasion

Background. Hepatocellular carcinoma (HCC), the most common primary liver cancer. In addition to its high incidence, the disease burden is high due to its poor prognosis and high recurrence rate. Some of the currently known clinicopathologic prognostic factors include alpha-fetoprotein (AFP) level, histologic grade, and microvascular invasion. At the molecular level, β-catenin is one of the most common driver mutation found in HCC. The Wnt/β-catenin pathway regulates cellular processes related to initiation, growth, survival, migration, differentiation, and apoptosis. Although the underlying pathogenesis of hepatocarcinogenesis is known, clinical application warrants a greater understanding of the molecular characteristics and tumor phenotype, especially for determining the prognosis. This study aims to analyze the expression of β-catenin and its association with AFP, histologic grade, and microvascular invasion. Materials and methods. Thirty-five samples of surgically resected HCCs at Cipto Mangunkusumo National Referral Hospital were examined. Diagnoses were made based on histopathological and immunohistochemical findings followed by β-catenin staining. β-catenin expression was analyzed to determine difference between variables. Results and conclusions. Here we show that β-catenin expression is significantly associated with low serum alpha-fetoprotein and well to moderate differentiation Implications. Strong nuclear β-catenin expression implies better prognosis in HCC.

Convolutional neural network for classifying primary liver cancer based on triple-phase CT and tumor marker information: a pilot study

PURPOSE

To develop convolutional neural network (CNN) models for differentiating intrahepatic cholangiocarcinoma (ICC) from hepatocellular carcinoma (HCC) and predicting histopathological grade of HCC.

MATERIALS AND METHODS

Preoperative computed tomography and tumor marker information of 617 primary liver cancer patients were retrospectively collected to develop CNN models categorizing tumors into three categories: moderately differentiated HCC (mHCC), poorly differentiated HCC (pHCC), and ICC, where the histopathological diagnoses were considered as ground truths. The models processed manually cropped tumor with and without tumor marker information (two-input and one-input models, respectively). Overall accuracy was assessed using a held-out dataset (10%). Area under the curve, sensitivity, and specificity for differentiating ICC from HCCs (mHCC + pHCC), and pHCC from mHCC were also evaluated. We assessed two radiologists' performance without tumor marker information as references (overall accuracy, sensitivity, and specificity). The two-input model was compared with the one-input model and radiologists using permutation tests.

RESULTS

The overall accuracy was 0.61, 0.60, 0.55, 0.53 for the two-input model, one-input model, radiologist 1, and radiologist 2, respectively. For differentiating pHCC from mHCC, the two-input model showed significantly higher specificity than radiologist 1 (0.68 [95% confidence interval: 0.50-0.83] vs 0.45 [95% confidence interval: 0.27-0.63]; p = 0.04).

CONCLUSION

Our CNN model with tumor marker information showed feasibility and potential for three-class classification within primary liver cancer.

Diagnostic Value of Imaging Methods in the Histological Four Grading of Hepatocellular Carcinoma

We attempted to establish an ultrasound (US) imaging-diagnostic system for histopathological grades of differentiation of hepatocellular carcinoma (HCC). We conducted a retrospective study of histopathologically confirmed 200 HCCs, classified as early (45 lesions), well- (31 lesions), moderately (68 lesions) or poorly differentiated (diff.) (56 lesions) HCCs. We performed grayscale US to estimate the presence/absence of halo and mosaic signs, Sonazoid contrast-enhanced US (CEUS) to determine vascularity (hypo/iso/hyper) of lesion in arterial and portal phase (PP), and echogenicity of lesion in post-vascular phase (PVP). All findings were of significance for the diagnosis of some (but not all) histological grades (p < 0.001–0.05). Combined findings with a relatively high diagnostic efficacy for early, poorly and moderately diff. HCC were a combination of absence of halo sign and isoechogenicity in PVP of CEUS (accuracy: 93.0%, AUC: 0.908), hypovascularity in PP (accuracy: 78.0%, area under the curve (AUC): 0.750), and a combination of isovascularity in PP and hypoechogenicity in PVP (accuracy: 75.0%, AUC: 0.739), respectively. On the other hand, neither any individual finding nor any combination of findings yielded an AUC of over 0.657 for the diagnosis of well-diff. HCC. Our study provides encouraging data on Sonazoid CEUS in the histological differential diagnosis of HCC, especially in early HCC, and the effectiveness of this imaging method should be further proved by prospective, large sample, multicenter studies.

A phenotypical map of disseminated hepatocellular carcinoma suggests clonal constraints in metastatic sites

AIMS

Access to tissue in patients with hepatocellular carcinoma (HCC) is limited compared to other malignancies, particularly at advanced stages. This has precluded a thorough characterisation of molecular drivers of HCC dissemination, particularly in relation to distant metastases. Biomarker assessment is restricted to early stages, and paired primary-metastatic comparisons between samples from the same patient are difficult.

METHODS AND RESULTS

We report the evaluation of 88 patients with HCC who underwent autopsy, including multiregional sampling of primary and metastatic sites totalling 230 nodules analysed. The study included morphological assessment, immunohistochemistry and mutation status of the TERT promoter, the most frequently mutated gene in HCC. We confirm a strong predilection of HCC for lung dissemination, including subclinical micrometastases (unrecognised during imaging and macroscopic examinations) in 30% of patients with disseminated disease. Size of dominant tumour nodule; multinodularity; macrovascular invasion; high histological, nuclear and architectural grades; and cellular crowding were associated with the presence of extrahepatic metastasis. Among the immunohistochemistry markers tested, metastatic nodules had significantly higher K19 and EpCAM expression than primary liver tumours. Morphological and immunohistochemical features showed that metastatic HCC could be traced back to the primary tumour, sometimes to a specific hepatic nodule.

CONCLUSIONS

This study suggests limited heterogeneity in metastatic sites compared to primary tumour sites.

The Impact of Tumor Differentiation on the Prognosis of HBV-Associated Solitary Hepatocellular Carcinoma Following Hepatectomy: A Propensity Score Matching Analysis

AIM

The role of tumor differentiation in the prognosis of hepatocellular carcinoma (HCC) after hepatectomy remains controversial. The present study aimed to classify the impact of tumor differentiation on solitary hepatitis B viral (HBV)-associated HCC using propensity score matching analysis.

METHODS

Between January 2009 and March 2015, the data of 721 HCC patients in West China Hospital were prospectively collected and analyzed. Propensity matching analysis was applied to overcome the imbalance in baseline characteristics. Survival analysis was performed using the Kaplan-Meier method. Risk factors were identified by the Cox proportional hazards model.

RESULTS

All HCC patients were classified into the moderately well-differentiated HCCs group (group A, n = 442, 61.3%) or poorly differentiated HCCs group (group B, n = 279, 38.7%). Patients with poorly differentiated HCCs commonly had a larger tumor size, more advanced tumors, and a higher alpha-fetoprotein (AFP) level. Patients with poorly differentiated HCCs had a poorer recurrence-free survival and overall survival before and after propensity score matching analysis. Poorly differentiated tumors, positive serum hepatitis B viral e antigen, positive hepatitis B virus deoxyribonucleic acid load, tumor size, microvascular invasion, and AFP > 400 ng/ml were risk factors of a poor outcome.

CONCLUSIONS

Our propensity model provided strong evidence that a poorly differentiated tumor had a negative impact on the recurrence and long-term survival of solitary HBV-associated HCCs after curative hepatectomy. Antiviral therapy might improve their prognosis.

Histological Grading of Hepatocellular Carcinoma-A Systematic Review of Literature

Background

Histological grading typically reflects the biological behavior of solid tumors, thus providing valuable prognostic information. This is also expected in hepatocellular carcinoma (HCC), although limited access to biopsy samples and a lack of standardization might hinder its full predictive value in this cancer.

Objectives

In order to better understand the current practices of histological grading in HCC, we examined the latest publications addressing its impact on the outcome of patients following surgical treatment.

Methods

We searched the PubMed (MEDLINE) database under the headings “hepatocellular carcinoma,” “grade OR grading,” and “prognosis.” Qualitative and quantitative assessment of publications was performed according to the reference they used to grade their tumors (e.g., Edmondson–Steiner, World Health Organization).

Results

We reviewed a total of 216 articles: 114 enclosed adequate information and were included herein. Among these, we found divergences and inaccuracies in the histological grade assessment of this cancer, which might have led to a non-standardized grade distribution, with further impact on data analysis. Nevertheless, in most of them, poor tumor differentiation correlated with worse prognosis, expressed by lower overall and/or disease-free survival.

Conclusion

While histological grading of HCC has an important prognostic role, there is an unsatisfactory heterogeneity on the microscopic assessment of this tumor, urging for a movement toward standardization.

Hedgehog signaling pathway affects the sensitivity of hepatoma cells to drug therapy through the ABCC1 transporter

The poor response to drug therapy often seen in hepatocellular carcinoma requires insight into the molecular interplay responsible for intrinsic or acquired drug resistance. We previously demonstrated that the CD133^-/EpCAM^- subpopulation of the Huh-7 hepatoma cell line features aberrant activation of the hedgehog signaling (Hh) pathway and chemoresistance. The prevailing hypothesis of the present study is that hedgehog signaling may govern expression of ATP-binding cassette (ABC) transporters, which are responsible for drug resistance in the CD133^-/EpCAM^- subpopulation. Our aim is to reveal the molecular interplay in the mediation of drug resistance with a newly established Huh-7 subpopulation featuring high Hh signaling activity and drug resistance. In this study, chemoresistance was determined in a newly established Huh-7-DN subpopulation featuring the CD133^-/EpCAM^- surface marker profile, aberrant expression of Hh pathway, and epithelial-mesenchymal transition (EMT). Expression of ABC transporter proteins (ABCB1, ABCC1, and ABCG2) and Hh transcription factor Gli-1/2 was evaluated with and without Hh signaling antagonists LDE225 or itraconazole. We found that hedgehog signaling activity as determined by transfection with a Gli-Lux reporter cassette and gene expression levels tended to increase from Huh-7 CD133⁺/EpCAM⁺ to CD133^-/EpCAM^-, and the highest levels were found in Huh-7-DN cells. The Huh-7-DN subpopulation exhibited characteristics of EMT as evidenced by increased expression of vimentin and loss of E-cadherin. Sorafenib significantly inhibited the viability of all subpopulations except the Huh-7-DN subpopulation. Compared with other sorafenib-sensitive subpopulations, the Huh-7-DN subpopulation showed enhanced expression of Hh transcription factor Gli-2 and ABCC1 transporter protein. Silencing Gli-2 by lentivirus harboring shRNA against Gli-2 or LDE225 significantly suppressed expression of Gli-2 and ABCC1 genes in Huh-7-DN subpopulation. In conclusion, aberrant hedgehog signaling activation is linked to poor differentiation, epithelial-mesenchymal transition, and chemoresistance in the Huh-7-DN subpopulation. Hedgehog signaling transcription factor Gli-2 appears to be the primary regulator for drug sensitivity of hepatoma through the ABCC1 transporter.

Imaging of the postoperative liver: review of normal appearances and common complications

Several benign and malignant liver diseases may require surgical treatment for cure, including anatomical resections based on the segmental anatomy of the liver, non-anatomical (wedge) resections, and surgical management of biliary cysts. The type of surgery depends not only on the location and the nature of the disease, but also on the expertise of the surgeon. Whereas ultrasonography is often the first-line imaging examination in case of suspected postoperative complication, multidetector computed tomography (MDCT) is of greater value for identifying normal findings after surgery, early postoperative pathologic fluid collections and vascular thromboses, and tumor recurrence in patients who have undergone hepatic surgery. Magnetic resonance cholangiopancreatography (MRCP) is the imaging modality of choice for depicting early postoperative bile duct injuries and ischemic cholangitis that may occur in the late postoperative phase. Both MDCT and MRCP can accurately depict tumor recurrence. Radiologists should become familiar with these surgical procedures to better understand postoperative changes, and with the normal imaging appearances of various postoperative complications to better differentiate between complications and normal findings.

The predictive value of metabolic tumor volume on FDG PET/CT for transarterial chemoembolization and transarterial chemotherapy infusion in hepatocellular carcinoma patients without extrahepatic metastasis

OBJECTIVE

The aim of this study was to evaluate the prognostic value of metabolic tumor volume (MTV) on pre-treatment F-18 fluorodeoxyglucose (FDG) PET/CT in patients with hepatocellular carcinoma (HCC).

METHODS

A total of 59 HCC patients who underwent FDG PET/CT before transarterial chemoembolization (TACE) or transarterial chemotherapy infusion (TACI) were retrospectively enrolled. The region of interest was drawn in the HCC and normal liver tissue. MTV2SD, defined as the sum of the voxels with higher standardized uptake values (SUV) than the SUV of the 97.5th percentile of voxels of the normal liver for each patient, was calculated using an intensity-volume histogram (IVH). The ratio of the maximum SUV of the tumor to the mean SUV of normal liver (T max/L mean) was also calculated. The prognostic significance of MTV2SD and Tmax/Lmean for progression-free survival (PFS) and overall survival (OS) was evaluated along with other clinical factors.

RESULTS

The tumor number, Tmax/Lmean, and MTV2SD were significant prognostic factors affecting PFS (p < 0.05), whereas tumor number, serum alpha-fetoprotein level, tumor stage, portal vein thrombosis, Tmax/Lmean, and MTV2SD were significant prognostic factors for OS (p < 0.05). In multivariate analysis, the tumor number and MTV2SD were independent prognostic factors for PFS (p < 0.05), whereas the independent prognostic factors for OS were tumor number, tumor stage, and MTV2SD (p < 0.05). The mean PFS and OS in patients with low MTV2SD (15.4 and 63.1 months, respectively) were significantly longer than those in patients with high MTV2SD (6.0 and 15.2 months, respectively; p = 0.005 and p < 0.0001, respectively).

CONCLUSIONS

Metabolic tumor volume was an independent prognostic factor for PFS and OS in patients with HCC. Therefore, FDG PET/CT can provide valuable prognostic information for HCC patients who undergo TACE or TACI.

Role of antiviral therapy in reducing recurrence and improving survival in hepatitis B virus-associated hepatocellular carcinoma following curative resection (Review)

Hepatocellular carcinoma (HCC) is one of the major causes of cancer-related mortality worldwide, with the majority of cases associated with persistent hepatitis B virus (HBV) or hepatitis C virus infection. In particular, chronic HBV infection is a predominant risk factor for the development of HCC in Asian and African populations. Hepatic resection, liver transplantion and radiofrequency ablation are increasingly used for the curative treatment of HCC, however, the survival rate of HCC patients who have undergone curative resection remains unsatisfactory due to the high recurrence rate. HCC is a complex disease that is typically resistant to the most commonly used types of chemotherapy and radiotherapy; therefore, the development of novel treatment strategies is required to improve the survival rate of this disease. A high viral load of HBV DNA is the most important correctable risk factor for HCC recurrence, for example nucleos(t)ide analogs improve the outcome following curative resection of HBV-associated HCC, and interferon-α exhibits antitumor activity against various types of cancer via direct inhibitory effects on tumor cells, anti-angiogenesis, enhanced immunogenicity of tumors, immunomodulatory effects and liver dysfunction. In the present review, antiviral treatment for HBV-associated HCC is described as a strategy to reduce recurrence and improve survival.

Diagnosis system for hepatocellular carcinoma based on fractal dimension of morphometric elements integrated in an artificial neural network

BACKGROUND AND AIMS

Hepatocellular carcinoma (HCC) remains a leading cause of death by cancer worldwide. Computerized diagnosis systems relying on novel imaging markers gained significant importance in recent years. Our aim was to integrate a novel morphometric measurement--the fractal dimension (FD)--into an artificial neural network (ANN) designed to diagnose HCC.

MATERIAL AND METHODS

The study included 21 HCC and 28 liver metastases (LM) patients scheduled for surgery. We performed hematoxylin staining for cell nuclei and CD31/34 immunostaining for vascular elements. We captured digital images and used an in-house application to segment elements of interest; FDs were calculated and fed to an ANN which classified them as malignant or benign, further identifying HCC and LM cases.

RESULTS

User intervention corrected segmentation errors and fractal dimensions were calculated. ANNs correctly classified 947/1050 HCC images (90.2%), 1021/1050 normal tissue images (97.23%), 1215/1400 LM (86.78%), and 1372/1400 normal tissues (98%). We obtained excellent interobserver agreement between human operators and the system.

CONCLUSION

We successfully implemented FD as a morphometric marker in a decision system, an ensemble of ANNs designed to differentiate histological images of normal parenchyma from malignancy and classify HCCs and LMs.