A Predictive Nomogram of Early Recurrence for Patients with AFP-Negative Hepatocellular Carcinoma Underwent Curative Resection.
Diagnostics (Basel, Switzerland)
BACKGROUND:Alpha-fetoprotein-negative (<20 ng/mL) hepatocellular carcinoma (AFP-NHCC) cannot be easily diagnosed in clinical practice, which may affect early treatment and prognosis. Furthermore, there are no reliable tools for the prediction of AFP-NHCC early recurrence that have been developed currently. The objective of this study was to identify the independent risk factors for AFP-NHCC and construct an individual prediction nomogram of early recurrence of these patients who underwent curative resection. METHODS:A retrospective study of 199 patients with AFP-NHCC who had undergone curative resection and another 231 patients with AFP-positive HCC were included in case-controlled analyses. All AFP-NHCC patients were randomly divided into training and validation datasets at a ratio of 7:3. The univariate and multivariate Cox proportional hazards regression analyses were applied to identify the risk factors, based on which the predictive nomogram of early recurrence was constructed in the training dataset. The area under the curve (AUC), calibration curve, and decision curve was used to evaluate the predictive performance and discriminative ability of the nomogram, and the results were validated in the validation dataset. RESULTS:Compared to AFP-positive patients, the AFP-negative group with lower values of laboratory parameters, lower tumor aggressiveness, and less malignant magnetic resonance (MR) imaging features. AST (HR = 2.200, = 0.009), tumor capsule (HR = 0.392, = 0.017), rim enhancement (HR = 2.825, = 0.002) and TTPVI (HR = 5.511, < 0.001) were independent predictors for early recurrence of AFP-NHCC patients. The nomogram integrated these independent predictors and achieved better predictive performance with AUCs of 0.89 and 0.85 in the training and validation datasets, respectively. The calibration curve and decision curve analysis both demonstrated better predictive efficacy and discriminative ability of the nomogram. CONCLUSIONS:The nomogram based on the multivariable Cox proportional hazards regression analysis presented accurate individual prediction for early recurrence of AFP-NHCC patients after surgery. This nomogram could assist physicians in personalized treatment decision-making for patients with AFP-NHCC.
Diagnostic Value of Combined Detection via Protein Induced by Vitamin K Absence or Antagonist II, Alpha-Fetoprotein, and D-Dimer in Hepatitis B Virus-Related Hepatocellular Carcinoma.
International journal of general medicine
Purpose:We aimed to explore the clinical diagnostic value of combined detection via protein induced by vitamin K absence or antagonist II (PIVKA-II), alpha-fetoprotein (AFP), and D-dimer (D-D) in hepatitis B virus (HBV)-related hepatocellular carcinoma (HCC). Materials and Methods:We analyzed PIVKA-II, AFP, and D-D levels in 291 subjects comprising liver cirrhosis (LC) patients (n = 143) and HCC patients (n = 148). Receiver operating characteristic (ROC) curves were used to analyze and compare the clinical diagnostic value of the three biomarkers for HBV-related HCC alone and in combination. Results:The levels of PIVKA-II, AFP, and D-D were positively correlated with tumor size in HCC patients. The levels of PIVKA-II and AFP in early-stage HCC, advanced HCC, HBV DNA+ HCC, and HBV DNA- HCC patients were higher than those in LC patients, while the levels of D-D were lower. The area under the curve for combined detection was greater than that for single-index detection in early-stage HCC, advanced HCC, HBV DNA+ HCC, and HBV DNA- HCC patients. Conclusion:D-D may be a useful biomarker for the diagnosis of HBV-related HCC. The combined detection of PIVKA-II, AFP, and D-D had better diagnostic value for different types of HCC than the detection of individual biomarkers.
The Fibrinogen/Albumin Ratio Index as an Independent Prognostic Biomarker for Patients with Combined Hepatocellular Cholangiocarcinoma After Surgery.
Cancer management and research
Purpose:The fibrinogen/albumin ratio (FAR) is increasingly considered as a potential biomarker for predicting prognosis in various malignant tumors, whereas the value of the FAR in predicting the recurrence-free survival (RFS) in patients with combined hepatocellular cholangiocarcinoma (cHCC-CCA) after surgery has not been studied. Patients and Methods:A total of 104 patients with surgical-pathologically proved cHCC-CCA were retrospectively analyzed. The best cut-off value of the FAR was calculated via receiver operating characteristic (ROC) curve analysis, and the cohort was then divided into two groups as high-FAR (H-FAR) group and low-FAR (L-FAR) group. The correlation between the preoperative FAR and clinicopathological characteristics was analyzed. Uni- and multi-variable analyses for RFS were evaluated using a Cox proportional hazards model to verify the predictive value of FAR on the RFS of cHCC-CCA. Additionally, a novel clinical nomogram based on FAR was developed to preoperatively predict the RFS of HCC-CCA. The C-index and calibration were conducted to evaluate the performance of the developed nomogram. Results:According to the cut-off value of the FAR, the patients were grouped into the H-FARI (>0.075) and L-FARI (≤0.075) groups. FAR was significantly correlated with several clinical-pathological features, including age, cirrhosis, AFP, CA19-9, BCLC staging, NLR, and PLR. In the multi-variate analysis, FAR, cirrhosis and tumor size were independent prognostic predictors for poor RFS in cHCC-CCA patients after surgery. Moreover, the clinical nomogram based on FAR was constructed, showing well-predictive accuracy. Conclusion:The preoperative FAR is a convenient and feasible serum biomarker for predicting the RFS of cHCC-CCA after surgery. Such developed FAR-based nomogram integrating tumor size and cirrhosis could be served as a feasible and convenient tool to assist the decision-making of clinical strategy.
Microwave ablation as bridging to liver transplant for patients with hepatocellular carcinoma: a single-center retrospective analysis.
Journal of vascular and interventional radiology : JVIR
PURPOSE:To evaluate the efficacy and safety of microwave (MW) ablation as first-line locoregional therapy (LRT) for bridging patients with hepatocellular carcinoma (HCC) to liver transplant. MATERIALS AND METHODS:This retrospective study evaluated 88 patients who received percutaneous MW ablation for 141 tumors as first-line LRT for HCC and listed for liver transplantation at a single medical center between 2011 and 2019. Overall survival rate status-post liver transplant, waitlist retention and disease progression were evaluated using Kaplan-Meier techniques. RESULTS:Of 88 patients (72M, 16F, mean age 60 years, MELD=11.2) listed for transplant, median waitlist time was 9.4 months (IQR: 5.5 - 18.9). Seventy-one patients (80.7%) received transplant after median wait time of 8.5 months. Seventeen patients (19.3%) were removed from the waitlist, four (4.5%) due to tumors outside of the Milan criteria (HCC-specific dropout). No difference in tumor size or AFP was seen in transplanted vs. non-transplanted patients at time of ablation (2.1 vs. 2.1 cm and 34.4 vs. 34.7 ng/mL for transplanted vs. non-transplanted, respectively, p>0.05). Five of 88 patients (5.1%) experienced adverse events after ablation; however, all recovered. There were no cases of tract seeding. The local tumor progression (LTP) rate was 7.2%. The overall survival status-post liver transplant at 5-years was 76.7% and the disease-specific survival after LT was 89.6% with a median follow-up of 61 months for all patients. CONCLUSION:MW ablation appears to be safe and effective for bridging patients with HCC to liver transplant without waitlist removal from seeding, adverse events, or local tumor progression.
Circulating microRNAs (miR-16, miR-22, miR-122) expression and early diagnosis of hepatocellular carcinoma.
Journal of clinical laboratory analysis
PURPOSE:Circulating microRNA (miRNA) has been reported to have diagnostic value in multiple tumors. To identify serum miRNAs for early diagnosis of hepatocellular carcinoma (HCC), we analyzed the differential miRNA expression between HCC patients and controls. METHODS:Real-time reverse transcription polymerase chain reaction (RT-PCR) was carried out to detect serum miR-16, miR-22, and miR-122 expression in 100 HCC patients and 100 controls (including hepatitis B, liver cirrhosis, liver metastases, hepatic hemangioma, health group, and each of them had 20 subjects). The miRNA expression results were combined with alpha-fetoprotein (AFP) to evaluate the diagnostic efficacy in HCC through receiver operating characteristic (ROC) curve. And the target genes were predicted through bioinformatics methods. RESULTS:Compared with controls, the expression of miR-16 and miR-122 significantly increased in early-stage HCC patients, while no significant changes were detected in miR-22. The ROC curve analysis demonstrated that miR-16 and miR-122 had a high diagnostic efficacy (AUC 0.798 and 0.759), and it was improved when combined with AFP (AUC 0.862). When compared with each of the five groups in the controls, the results showed that miR-16 of HCC was significantly higher than liver cirrhosis (AUC 0.936), liver metastases, and health; miR-122 was significantly higher than liver metastases, hepatitis B, and health. Moreover, 175 and 101 potential target genes were regulated by miR-16 and miR-122, respectively. And most of the target genes were enriched in the PI3K, MAPK, FoxO signaling pathways, and pathways in cancer. CONCLUSION:Our findings illustrate that both circulating miR-16 and miR-122 can provide value for early diagnosis of HCC and they are potential biomarkers for the early-stage HCC.
Diagnostic Value of Multislice Spiral Computed Tomography Combined with Serum AFP, TSGF, and GP73 Assay in the Diagnosis of Primary Liver Cancer.
Evidence-based complementary and alternative medicine : eCAM
Objective:To explore the diagnostic value of multislice spiral computed tomography (MSCT) scan combined with serum alpha-fetoprotein (AFP), tumor-specific growth factor (TSGF), and Golgi protein73 (GP73) assays in the diagnosis of primary liver cancer (PLC). Methods:Totally, 60 patients with PLC admitted to The Second Hospital of Dalian Medical University from January 2019 to January 2020 were included in group A, 60 patients with liver cirrhosis were included in group B, and 60 healthy subjects were included in group C. The serum AFP, TSGF, and GP73 levels were determined, and all participants received MSCT scanning. The diagnostic efficacy of MSCT, assays of serum AFP, TSGF, and GP73, and their combined detection was analyzed. Results:Group A had the highest levels of AFP, TSGF, and GP73, followed by group B, and then group C. The sensitivity, specificity, positive predictive value, and negative predictive value of MSCT for PLC were 80.0%,91.7%, 82.8%, and 90.2%, respectively, while those of combined detection of MSCT plus serum AFP, TSGF, and GP73 for PLC were 100.0%, 93.3%, 88.2%, and 100.0%. The combined detection was associated with significantly a higher detection rate of PLC versus stand-alone detection. Conclusion:MSCT plus serum AFP, TSGF, and GP73 has a higher detection rate versus stand-alone detection, which shows great potential in the diagnosis of PLC.
Deep-learning-based analysis of preoperative MRI predicts microvascular invasion and outcome in hepatocellular carcinoma.
World journal of surgical oncology
BACKGROUND:Preoperative prediction of microvascular invasion (MVI) is critical for treatment strategy making in patients with hepatocellular carcinoma (HCC). We aimed to develop a deep learning (DL) model based on preoperative dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) to predict the MVI status and clinical outcomes in patients with HCC. METHODS:We retrospectively included a total of 321 HCC patients with pathologically confirmed MVI status. Preoperative DCE-MRI of these patients were collected, annotated, and further analyzed by DL in this study. A predictive model for MVI integrating DL-predicted MVI status (DL-MVI) and clinical parameters was constructed with multivariate logistic regression. RESULTS:Of 321 HCC patients, 136 patients were pathologically MVI absent and 185 patients were MVI present. Recurrence-free survival (RFS) and overall survival (OS) were significantly different between the DL-predicted MVI-absent and MVI-present. Among all clinical variables, only DL-predicted MVI status and a-fetoprotein (AFP) were independently associated with MVI: DL-MVI (odds ratio [OR] = 35.738; 95% confidence interval [CI] 14.027-91.056; p < 0.001), AFP (OR = 4.634, 95% CI 2.576-8.336; p < 0.001). To predict the presence of MVI, DL-MVI combined with AFP achieved an area under the curve (AUC) of 0.824. CONCLUSIONS:Our predictive model combining DL-MVI and AFP achieved good performance for predicting MVI and clinical outcomes in patients with HCC.
Prediction Model and Nomogram of Early Recurrence of Hepatocellular Carcinoma after Radiofrequency Ablation Based on Logistic Regression Analysis.
Ultrasound in medicine & biology
The purpose of this study was to screen for high-risk factors leading to the early recurrence of hepatocellular carcinoma (HCC) after radiofrequency ablation (RFA) and to construct a prediction model and nomogram. This retrospective study included 108 patients with primary HCC who underwent RFA treatment at the Harbin Medical University Cancer Hospital between January 2018 and June 2019. Four risk factors were screened for using univariate and multivariate logistic regression analyses: number of tumors (hazard ratio [HR] = 14.684, 95% confidence interval [CI]: 1.099-196.215, p = 0.042), neutrophil-to-lymphocyte ratio (NLR) (HR = 2.178, 95% CI: 1.003-4.730, p = 0.049), contrast-enhanced ultrasound (CEUS) performance (HR = 6.482, 95% CI: 1.161-36.184, p = 0.033) and α-fetoprotein (AFP) level (HR = 1.001, 95% CI: 1.000-1.003, p = 0.040). We established a prediction model: Logit(p) = -3.096 + 2.827 × (number of tumors >1 = 1) + 1.851 × (CEUS revealing rapid enhancement of blood flow signal in the arterial phase and clearance in the portal phase = 1) + 1.941 × (NLR >1.55 = 1) + 0.257 × (AFP >32.545 = 1). Through clinical decision curve analysis, the model's threshold was 0.043-0.873, indicating a high clinical value. Patients with a high AFP level, typical CEUS enhancement pattern, multiple tumors and elevated NLR are more likely to relapse early.
A highly sensitive silicon nanowire array sensor for joint detection of tumor markers CEA and AFP.
Liver cancer is one of the malignant tumors with the highest fatality rate and increasing incidence, which has no effective treatment plan. Early diagnosis and early treatment of liver cancer play a vital role in prolonging the survival period of patients and improving the cure rate. Carcinoembryonic antigen (CEA) and alpha-fetoprotein (AFP) are two crucial tumor markers for liver cancer diagnosis. In this work, we firstly proposed a wafer-level, highly controlled silicon nanowire (SiNW) field-effect transistor (FET) joint detection sensor for highly sensitive and selective detection of CEA and AFP. The SiNWs-FET joint detection sensor possesses 4 sensing regions. Each sensing region consists of 120 SiNWs arranged in a 15 × 8 array. The SiNW sensor was developed by using a wafer-level and highly controllable top-down manufacturing technology to achieve the repeatability and controllability of device preparation. To identify and detect CEA/AFP, we modified the corresponding CEA antibodies/AFP antibodies to the sensing region surface after a series of surface modification processes, including O plasma treatment, soaking in 3-aminopropyltriethoxysilane (APTES) solution, and soaking in glutaraldehyde (GA) solution. The experimental results showed that the SiNW array sensor has superior sensitivity with a real-time ultralow detection limit of 0.1 fg ml (AFP in 0.1× PBS) and 1 fg ml (CEA in 0.1× PBS). Also, the logarithms of the concentration of CEA (from 1 fg ml to 10 pg ml) and AFP (from 0.1 fg ml to 100 pg ml) achieved conspicuously linear relationships with normalized current changes. The of AFP in 0.1× PBS and of CEA in 0.1× PBS were 0.99885 and 0.99677, respectively. Furthermore, the sensor could distinguish CEA/AFP from interferents at high concentrations. Importantly, even in serum samples, our sensor could successfully detect CEA/AFP. This demonstrates the promising clinical development of our sensor.
First-Line Targeted Therapy for Hepatocellular Carcinoma: Role of Atezolizumab/Bevacizumab Combination.
Hepatocellular carcinoma (HCC) is an aggressive malignancy accounting for 90% of primary liver malignancies. Therapeutic options for HCC are primarily based on the baseline functional status, the extent of disease at presentation and the underlying liver function that is clinically evaluated by the Barcelona-Clinic Liver Cancer system and Child-Pugh score. In patients with advanced HCC, the United States Food and Drug Administration (US-FDA) approved systemic therapies include the combination of atezolizumab-bevacizumab, sorafenib, and lenvatinib in the first line setting while cabozantinib, regorafenib, ramucirumab (in patients with alfa-fetoprotein [AFP] > 400 ng/mL), pembrolizumab, nivolumab, and nivolumab-ipilimumab combination are reserved for patients who progressed on sorafenib. European Medical Agency (EMA) approved the use of atezolizumab-bevacizumab, sorafenib, and lenvatinib in the first line setting, while cabozantinib, regorafenib, and ramucirumab (in patients with alfa-fetoprotein [AFP] > 400 ng/mL) are approved for use in patients that progressed on first-line therapy. In the first line setting, sorafenib demonstrated a median overall survival (OS) benefit of 3 months as compared to that of best supportive care in randomized phase III trials, while lenvatinib was shown to be non-inferior to sorafenib. Recently, phase 3 studies with immunotherapeutic agents including atezolizumab plus a bevacizumab combination and tremelimumab plus durvalumab combination demonstrated a better OS and progression free survival (PFS) compared to sorafenib in the first-line setting, making them attractive first-line options in advanced HCC. In this review, we outlined the tumorigenesis and immune landscape of HCC in brief and discussed the role and rationale of combining immunotherapy and anti-VEGF therapy. We further expanded on potential limitations and the future directions of immunotherapy in combination with targeted agents in the management of advanced HCC.
Molecular correlates of clinical response and resistance to atezolizumab in combination with bevacizumab in advanced hepatocellular carcinoma.
Atezolizumab (anti-programmed death-ligand 1 (PD-L1)) and bevacizumab (anti-vascular endothelial growth factor (VEGF)) combination therapy has become the new standard of care in patients with unresectable hepatocellular carcinoma. However, potential predictive biomarkers and mechanisms of response and resistance remain less well understood. We report integrated molecular analyses of tumor samples from 358 patients with hepatocellular carcinoma (HCC) enrolled in the GO30140 phase 1b or IMbrave150 phase 3 trial and treated with atezolizumab combined with bevacizumab, atezolizumab alone or sorafenib (multikinase inhibitor). Pre-existing immunity (high expression of CD274, T-effector signature and intratumoral CD8 T cell density) was associated with better clinical outcomes with the combination. Reduced clinical benefit was associated with high regulatory T cell (Treg) to effector T cell (Teff) ratio and expression of oncofetal genes (GPC3, AFP). Improved outcomes from the combination versus atezolizumab alone were associated with high expression of VEGF Receptor 2 (KDR), Tregs and myeloid inflammation signatures. These findings were further validated by analyses of paired pre- and post-treatment biopsies, in situ analyses and in vivo mouse models. Our study identified key molecular correlates of the combination therapy and highlighted that anti-VEGF might synergize with anti-PD-L1 by targeting angiogenesis, Treg proliferation and myeloid cell inflammation.
Prognostic impact of C-reactive protein and alpha-fetoprotein in immunotherapy score in hepatocellular carcinoma patients treated with atezolizumab plus bevacizumab: a multicenter retrospective study.
AIM:This study aimed to investigate the utility of C-reactive protein (CRP) and alpha-fetoprotein (AFP) in immunotherapy (CRAFITY) score in hepatocellular carcinoma (HCC) patients receiving atezolizumab and bevacizumab (Atez/Bev). METHODS:This retrospective cohort study included a total of 297 patients receiving Atez/Bev from September 2020 to November 2021 at 21 different institutions and hospital groups in Japan. Patients with AFP ≥ 100 ng/mL and those with CRP ≥ 1 mg/dL were assigned a CRAFITY score of 1 point. RESULTS:The patients were assigned CRAFITY scores of 0 points (n = 147 [49.5%]), 1 point (n = 111 [37.4%]), and 2 points (n = 39 [13.1%]). AFP ≥ 100 ng/mL and CRP ≥ 1.0 mg/dL were significantly associated with progression-free survival (PFS) and overall survival (OS). The median PFS in the CRAFITY score 0, 1, and 2 groups was 11.8 months (95% confidence interval [CI] 6.4-not applicable [NA]), 6.5 months (95% CI 4.6-8.0), and 3.2 months (95% CI 1.9-5.0), respectively (p < 0.001). The median OS in patients with CRAFITY score 0, 1 and 2 was not reached, 14.3 months (95% CI 10.5-NA), and 11.6 months (95% CI 4.9-NA), respectively. The percentage of patients with grade ≥ 3 liver injury, any grade of decreased appetite, any grade of proteinuria, any grade of fever, and any grade of fatigue was lowest in patients with a CRAFITY score of 0, followed by patients with CRAFITY scores of 1 and 2. CONCLUSIONS:The CRAFITY score is simple and could be useful for predicting therapeutic outcomes and treatment-related adverse events.
Circulating biomarkers in the diagnosis and management of hepatocellular carcinoma.
Nature reviews. Gastroenterology & hepatology
Hepatocellular carcinoma (HCC) is one of the most prevalent and lethal causes of cancer-related death worldwide. The treatment of HCC remains challenging and is largely predicated on early diagnosis. Surveillance of high-risk groups using abdominal ultrasonography, with or without serum analysis of α-fetoprotein (AFP), can permit detection of early, potentially curable tumours, but is limited by its insensitivity. Reviewed here are two current approaches that aim to address this limitation. The first is to use old re-emerged empirically derived biomarkers such as AFP, now applied within statistical models. The second is to use circulating nucleic acid biomarkers, which include cell-free DNA (for example, circulating tumour DNA, cell-free mitochondrial DNA and cell-free viral DNA) and cell-free RNA, applying modern molecular biology-based technologies and machine learning techniques closely allied to the underlying biology of cancer. Taken together, these approaches are likely to be complementary. Both hold considerable promise for achieving earlier diagnosis as well as offering additional functionalities including improved monitoring of therapy and prediction of response thereto.
Role of the pre- to postoperative alpha-fetoprotein ratio in the prognostic evaluation of liver cancer after radiofrequency ablation.
The International journal of biological markers
OBJECTIVE:This study aimed to investigate the role of the alpha fetoprotein (AFP) ratio before and after radiofrequency ablation (RFA) in the prognosis of patients with liver cancer. METHODS:A total of 368 patients who underwent RFA for liver cancer in Shenzhen People's Hospital from 2010 to 2020 were randomly divided into the training group and the validation group. Levels of AFP before and after RFA were recorded and their ratios were calculated. RESULTS:Using the X-tile software, it was found that the optimal cut-off value of the AFP ratio in the training group was 37.9. Both in the training group and the validation group, the relapse-free survival and overall survival of patients with an AFP ratio <37.9 (high-risk group) were significantly shorter than those with an AFP ratio >37.9 (low-risk group) (training group, relapse-free survival, = 0.0003; overall survival, = 0.0186; validation group, relapse-free survival, = 0.0490, overall survival, = 0.0031). An AFP ratio <37.9 was an independent risk factor for recurrence and survival of liver cancer after RFA. CONCLUSION:The AFP ratio can predict the prognosis of patients with liver cancer after RFA. An AFP ratio <37.9 is an independent risk factor for tumor recurrence and survival after RFA.
A functionalized magnetic nanoparticle regulated CRISPR-Cas12a sensor for the ultrasensitive detection of alpha-fetoprotein.
Alpha-fetoprotein (AFP) is an important clinical tumor marker of hepatoblastoma, and the concentration of AFP in serum is closely related to the staging of hepatoblastoma. We report a magnetic bead separation platform based on a switching aptamer triggered hybridization chain reaction (SAT-HCR) and the CRISPR-Cas12a sensor for the detection of AFP. AFP aptamer, as an easily regulated nucleic acid strand, is responsible for binding to AFP into nucleic acid detection, while HCR-CRISPR-Cas12a, regulated by functionalized magnetic nanoparticles, is responsible for highly specific nucleic acid signal amplification. Under the optimal conditions, the fluorescence intensity was proportional to the concentration of AFP in the range of 0.5-10 ng mL and the limit of detection was 0.170 ng mL. In addition, we have successfully applied this biosensor to detect AFP in clinical samples from patients with hepatoblastoma, with greater sensitivity relative to ELISA. Our proposed method showed great potential application in clinical diagnosis and pharmaceutical-related fields with the properties of high sensitivity, low cost and high selectivity.
IVIM using convolutional neural networks predicts microvascular invasion in HCC.
OBJECTIVES:The study aimed to investigate the diagnostic performance of intravoxel incoherent motion (IVIM) diffusion-weighted magnetic resonance imaging for prediction of microvascular invasion (MVI) in hepatocellular carcinoma (HCC) using convolutional neural networks (CNNs). METHODS:This retrospective study included 114 patients with pathologically confirmed HCC from December 2014 to August 2021. All patients underwent MRI examination including IVIM sequence with 9 b-values preoperatively. First, 9 b-value images were superimposed in the channel dimension, and a b-value volume with a shape of 32 × 32 × 9 dimension was obtained. Secondly, an image resampling method was performed for data augmentation to generate more samples for training. Finally, deep features to predict MVI in HCC were directly derived from a b-value volume based on the CNN. Moreover, a deep learning model based on parameter maps and a fusion model combined with deep features of IVIM, clinical characteristics, and IVIM parameters were also constructed. Receiver operating characteristic (ROC) curve analysis was performed to assess the diagnostic performance for MVI prediction in HCC. RESULTS:Deep features directly extracted from IVIM-DWI (0.810 (range 0.760, 0.829)) using CNN yielded better performance for prediction of MVI than those from IVIM parameter maps (0.590 (range 0.555, 0.643)). Furthermore, the performance of the fusion model combined with deep features of IVIM-DWI, clinical features (α-fetoprotein (AFP) level and tumor size), and apparent diffusion coefficient (ADC) (0.829 (range 0.776, 0.848)) was slightly improved. CONCLUSIONS:Deep learning with CNN based on IVIM-DWI can be conducive to preoperative prediction of MVI in patients with HCC. KEY POINTS:• Deep learning assessment of IVIM data for prediction of MVI in HCC can overcome the unstable and low performance of IVIM parameters. • Deep learning model based on IVIM performs better than parameter values, clinical features, and deep learning model based on parameter maps. • The fusion model combined with deep features of IVIM, clinical characteristics, and ADC yields better performance for prediction of MVI than the model only based on IVIM.
Prognostic Significance of Preoperative Integrated Liver Inflammatory Score in Patients with Hepatocellular Carcinoma.
Medical science monitor : international medical journal of experimental and clinical research
BACKGROUND The Integrated Liver Inflammatory Score (ILIS), which includes 5 serum indicators (albumin, bilirubin, neutrophil count, alpha-fetoprotein [AFP], and alkaline phosphatase [ALP]), is a novel inflammation-based predictive model associated with poor survival in hepatocellular carcinoma (HCC) patients. Our study aimed to assess the prognostic value of ILIS in HCC patients undergoing radical hepatectomy and establish a nomogram and artificial neural network based on their ILIS scores. MATERIAL AND METHODS This multicenter retrospective study included patients from 2 institutions from 2007 to 2017. Independent risk factors associated with Recurrence-free survival (RFS) and overall survival (OS) were identified through univariate and multifactor analysis in the training and validation groups, respectively. Afterward, column line graphs and artificial neural networks (ANN) were constructed and validated using the validation group. RESULTS A total of 432 patients were included in this study (275 in the training group and 157 in the validation group). In both cohorts, ILIS was correlated with pathological features such as tumor size, degree of differentiation, Child-Pugh class classification, and BCLC staging. Moreover, ILIS was identified as an independent risk factor for OS. ILIS-based nomograms and artificial neural networks also showed the prognostic value of ILIS. CONCLUSIONS Preoperative ILIS is an independent and effective predictor of prognosis in HCC patients treated with radical hepatectomy, as shown by the fact that higher ILIS are associated with worse patient prognosis. We have also established nomograms and ANNs that predict HCC prognosis with high accuracy.