Early Recurrence Of Hepatocellular Carcinoma Research Articles

Assessing microvascular invasion in HBV-related hepatocellular carcinoma: an online interactive nomogram integrating inflammatory markers, radiomics, and convolutional neural networks.

The early recurrence of hepatocellular carcinoma (HCC) correlates with decreased overall survival. Microvascular invasion (MVI) stands out as a prominent hazard influencing post-resection survival status and metastasis in patients with HBV-related HCC. The study focused on developing a web-based nomogram for preoperative prediction of MVI in HBV-HCC. 173 HBV-HCC patients from 2017 to 2022 with complete preoperative clinical data and Gadopentetate dimeglumine-enhanced magnetic resonance images were randomly divided into two groups for the purpose of model training and validation, using a ratio of 7:3. MRI signatures were extracted by pyradiomics and the deep neural network, 3D ResNet. Clinical factors, blood-cell-inflammation markers, and MRI signatures selected by LASSO were incorporated into the predictive nomogram. The evaluation of the predictive accuracy involved assessing the area under the receiver operating characteristic (ROC) curve (AUC), the concordance index (C-index), along with analyses of calibration and decision curves. Inflammation marker, neutrophil-to-lymphocyte ratio (NLR), was positively correlated with independent MRI radiomics risk factors for MVI. The performance of prediction model combined serum AFP, AST, NLR, 15 radiomics features and 7 deep features was better than clinical and radiomics models. The combined model achieved C-index values of 0.926 and 0.917, with AUCs of 0.911 and 0.907, respectively. NLR showed a positive correlation with MRI radiomics and deep learning features. The nomogram, incorporating NLR and MRI features, accurately predicted individualized MVI risk preoperatively.

Single-cell RNA sequencing reveals intratumoral heterogeneity and multicellular community in primary hepatocellular carcinoma underlying microvascular invasion

BackgroundMicrovascular invasion (MVI) is associated with an unfavorable prognosis and early recurrence of hepatocellular carcinoma (HCC), which is the crucial pathological hallmark of immunotherapy. While microvascular invasion (MVI) in hepatocellular carcinoma (HCC) currently lacks a detailed single-cell analysis of the tumor microenvironment (TME), it holds significant promise for immunotherapy using immune checkpoint inhibitors (ICI). MethodsWe performed single-cell RNA sequencing (scRNA-seq) on 3 MVI positive (MVIP) and 14 MVI-negative (MVIN) tumor tissues, as well as their paired adjacent non-tumoral tissues. ResultsWe identified SPP1+ macrophages and CD4+ proliferative T cells as intertumoral populations critical for the formation of cold tumors and immunosuppressive environments in MVI-positive patients and verified their prognostic value in correlation with MVIP HCC patients. Additionally, we identified SPP1+ dominated interactions between SPP1+ macrophages and the immunosuppressive T population as contributors to MVI destruction and tumorigenesis. ConclusionsWe provide a comprehensive single-cell atlas of HCC patients with MVI, shedding light on the immunosuppressive ecosystem and upregulated signaling associated with MVI. These findings demonstrate that intercellular mechanisms drive MVI and provide a potential immunotherapeutic target for HCC patients with HCC and underlying MVI.

A simple model to predict early recurrence of hepatocellular carcinoma after liver resection.

Multiple studies have reported models for predicting early recurrence of hepatocellular carcinoma (HCC) after liver resection (LR). However, these models are too complex to use in daily practice. We aimed to develop a simple model. We enrolled 1133 patients with newly diagnosed HCC undergoing LR. The Kaplan - Meier method and log-rank test were used for survival analysis and Cox proportional hazards analysis to identify prognostic factors associated with early recurrence (i.e., recurrence within two years after LR). Early recurrence was identified in 403 (35.1%) patients. In multivariate analysis, alpha-fetoprotein (AFP) 20-399 vs. < 20 ng/ml (HR = 1.282 [95% confidence interval = 1.002-1.639]; p = 0.048); AFP ≥ 400 vs. < 20 ng/ml (HR = 1.755 [1.382-2.229]; p < 0.001); 7th edition American Joint Committee on Cancer (AJCC) stage 2 vs. 1 (HR = 1.958 [1.505-2.547]; p < 0.001); AJCC stage 3 vs. 1 (HR = 4.099 [3.043-5.520]; p < 0.001); and pathology-defined cirrhosis (HR = 1.46 [1.200-1.775]; p < 0.001) were associated with early recurrence. We constructed a predictive model with these variables, which provided three risk strata for recurrence-free survival (RFS): low risk, intermediate risk, and high risk, with two-year RFS of 79%, 57%, and 35%, respectively (p < 0.001). We developed a simple model to predict early recurrence risk for patients undergoing LR for HCC.

Risk of early hepatocellular carcinoma recurrence following liver resection: arbitrary specification or possible target to improve outcome?

Risk of early hepatocellular carcinoma recurrence following liver resection: arbitrary specification or possible target to improve outcome?

Prediction power of radiomics in early recurrence of hepatocellular carcinoma: A systematic review and meta-analysis.

Raiomics is an emerging auxiliary diagnostic tool, but there are still differences in whether it can be applied to predict early recurrence of hepatocellular carcinoma (HCC). The purpose of this meta-analysis was to systematically evaluate the predictive power of radiomics in the early recurrence (ER) of HCC. Comprehensive studies on the application of radiomics to predict ER in HCC patients after hepatectomy or curative ablation were systematically screened in Embase, PubMed, and Web of Science. Ten studies which is involving a total of 1929 patients were reviewed. The overall estimates of radiomic models for sensitivity and specificity in predicting the ER of HCC were 0.79 (95% confidence interval [CI]: 0.68-0.87) and 0.83 (95% CI: 0.73-0.90), respectively. The area under the summary receiver operating characteristic curve (SROC) was 0.88 (95% CI: 0.85-0.91). The imaging method is a reliable method for diagnosing HCC. Radiomics, which is based on medical imaging, has excellent power in predicting the ER of HCC. With the help of radiomics, we can predict the recurrence of HCC after surgery more effectively and provide a useful reference for clinical practice.

Prediction Model and Nomogram of Early Recurrence of Hepatocellular Carcinoma after Ultrasound-guided Microwave Ablation

Ultrasound-guided microwave ablation (MWA) is recommended as a first-line treatment for early liver cancer due to its minimally invasive, efficient, and cost-effective nature. It utilizes microwave radiation to heat and destroy tumor cells as a local thermal therapy and offers the benefits of being minimally invasive, repeatable, and applicable to tumors of various sizes and locations. However, despite the efficacy of MWA, early recurrence after treatment remains a challenge, particularly when it occurs within a year and has a significant impact on the prognosis of the patient. This study aimed to identify the risk factors for early recurrence after MWA in patients with hepatocellular carcinoma (HCC) and establish a predictive model. A total of 119 patients with hepatocellular carcinoma (HCC) treated in the Department of Ultrasound at the First Affiliated Hospital of the Air Force Medical University from January, 2020 to April, 2022 were included in this study. Patients were categorized into the early recurrence group and the non-early recurrence group based on whether recurrence occurred within 1 year. We conducted univariate analysis on 29 variables. A predictive model was developed using multiple-factor logistic regression analysis, and a risk column graph was created. A total of 28 patients were included in the early recurrence group, with an early recurrence rate of 23%. Tumor size ≥ 3cm, multiple tumors, AST > 35 U/L, low pathological differentiation, CD34 positive, Ki67 level, quantitative parameters mean transit time (mTT), and rise time (RT) were confirmed as risk factors affecting early recurrence after ablation (P < 0.05). Furthermore, the model constructed based on these 5 predictive factors, including tumor size, tumor number, pathological differentiation, CD34, and quantitative analysis parameter mTT, demonstrated good predictive ability, with an AUC of 0.93 in the training set and 0.86 in the validation set. Our research indicates that the risk column graph can be utilized to predict the risk of early postoperative recurrence in patients after MWA. This contributes to guiding personalized clinical treatment decisions and provides important references for improving the prognosis of patients.

Decision-Tree Models Indicative of Microvascular Invasion on MRI Predict Survival in Patients with Hepatocellular Carcinoma Following Tumor Ablation.

Histological microvascular invasion (MVI) is a risk factor for poor survival and early recurrence in hepatocellular carcinoma (HCC) after surgery. Its prognostic value in the setting of locoregional therapies (LRT), where no tissue samples are obtained, remains unknown. This study aims to establish CT-derived indices indicative of MVI on liver MRI with superior soft tissue contrast and evaluate their association with patient survival after ablation via interstitial brachytherapy (iBT) versus iBT combined with prior conventional transarterial chemoembolization (cTACE). Ninety-five consecutive patients, who underwent ablation via iBT alone (n = 47) or combined with cTACE (n = 48), were retrospectively included between 01/2016 and 12/2017. All patients received contrast-enhanced MRI prior to LRT. Overall (OS), progression-free survival (PFS), and time-to-progression (TTP) were assessed. Decision-tree models to determine Radiogenomic Venous Invasion (RVI) and Two-Trait Predictor of Venous Invasion (TTPVI) on baseline MRI were established, validated on an external test set (TCGA-LIHC), and applied in the study cohorts to investigate their prognostic value for patient survival. Statistics included Fisher's exact and t-test, Kaplan-Meier and cox-regression analysis, area under the receiver operating characteristic curve (AUC-ROC) and Pearson's correlation. OS, PFS, and TTP were similar in both treatment groups. In the external dataset, RVI showed low sensitivity but relatively high specificity (AUC-ROC = 0.53), and TTPVI high sensitivity but only low specificity (AUC-ROC = 0.61) for histological MVI. In patients following iBT alone, positive RVI and TTPVI traits were associated with poorer OS (RVI: p < 0.01; TTPVI: p = 0.08), PFS (p = 0.04; p = 0.04), and TTP (p = 0.14; p = 0.03), respectively. However, when patients with combined cTACE and iBT were stratified by RVI or TTPVI, no differences in OS (p = 0.75; p = 0.55), PFS (p = 0.70; p = 0.43), or TTP (p = 0.33; p = 0.27) were observed. The study underscores the role of non-invasive imaging biomarkers indicative of MVI to identify patients, who would potentially benefit from embolotherapy via cTACE prior to ablation rather than ablation alone.

Preoperative and postoperative MRI-based models versus clinical staging systems for predicting early recurrence in hepatocellular carcinoma

BackgroundTo predict the early recurrence of HCC patients who received radical resection using preoperative variables based on Gd-EOB-DTPA enhanced MRI, followed by the comparison with the postoperative model and clinical staging systems. MethodsOne hundred and twenty-nine HCC patients who received radical resection were categorized into the early recurrence group (n = 48) and the early recurrence-free group (n = 81). Through COX regression analysis, statistically significant variables of laboratory, pathologic, and Gd-EOB-DTPA enhanced MRI results were identified. The preoperative and postoperative models were established to predict early recurrence, and the prognostic performances and differences were compared between the two models and clinical staging systems. ResultsSix variables were incorporated into the preoperative model, including alpha-fetoprotein (AFP) level, aspartate aminotransferase/platelet ratio index (APRI), rim arterial phase hyperenhancement (rim APHE), peritumoral hypointensity on hepatobiliary phase (HBP), CERHBP (tumor-to-liver SI ratio on hepatobiliary phase imaging), and ADC value. Moreover, the postoperative model was developed by adding microvascular invasion (MVI) and histological grade. The C-index of the preoperative model and postoperative model were 0.889 and 0.901 (p = 0.211) respectively. Using receiver operating characteristic curve analysis (ROC) and decision curve analysis (DCA), it was determined that the innovative models we developed had superior predictive capabilities for early recurrence in comparison to current clinical staging systems. HCC patients who received radical resection were stratified into low-, medium-, and high-risk groups on the basis of the preoperative and postoperative models. ConclusionThe preoperative and postoperative MRI-based models built in this study were more competent compared with clinical staging systems to predict the early recurrence in hepatocellular carcinoma.

Radiomics model based on contrast-enhanced computed tomography imaging for early recurrence monitoring after radical resection of AFP-negative hepatocellular carcinoma

BackgroundAlthough radical surgical resection is the most effective treatment for hepatocellular carcinoma (HCC), the high rate of postoperative recurrence remains a major challenge, especially in patients with alpha-fetoprotein (AFP)-negative HCC who lack effective biomarkers for postoperative recurrence surveillance. Emerging radiomics can reveal subtle structural changes in tumors by analyzing preoperative contrast-enhanced computer tomography (CECT) imaging data and may provide new ways to predict early recurrence (recurrence within 2 years) in AFP-negative HCC. In this study, we propose to develop a radiomics model based on preoperative CECT to predict the risk of early recurrence after surgery in AFP-negative HCC.Patients and methodsPatients with AFP-negative HCC who underwent radical resection were included in this study. A computerized tool was used to extract radiomic features from the tumor region of interest (ROI), select the best radiographic features associated with patient’s postoperative recurrence, and use them to construct the radiomics score (RadScore), which was then combined with clinical and follow-up information to comprehensively evaluate the reliability of the model.ResultsA total of 148 patients with AFP-negative HCC were enrolled in this study, and 1,977 radiographic features were extracted from CECT, 2 of which were the features most associated with recurrence in AFP-negative HCC. They had good predictive ability in both the training and validation cohorts, with an area under the ROC curve (AUC) of 0.709 and 0.764, respectively. Tumor number, microvascular invasion (MVI), AGPR and radiomic features were independent risk factors for early postoperative recurrence in patients with AFP-negative HCC. The AUCs of the integrated model in the training and validation cohorts were 0.793 and 0.791, respectively. The integrated model possessed the clinical value of predicting early postoperative recurrence in patients with AFP-negative HCC according to decision curve analysis, which allowed the classification of patients into subgroups of high-risk and low-risk for early recurrence.ConclusionThe nomogram constructed by combining clinical and imaging features has favorable performance in predicting the probability of early postoperative recurrence in AFP-negative HCC patients, which can help optimize the therapeutic decision-making and prognostic assessment of AFP-negative HCC patients.

Prediction model of early recurrence of multimodal hepatocellular carcinoma with tensor fusion

Objective. In oncology, clinical decision-making relies on a multitude of data modalities, including histopathological, radiological, and clinical factors. Despite the emergence of computer-aided multimodal decision-making systems for predicting hepatocellular carcinoma (HCC) recurrence post-hepatectomy, existing models often employ simplistic feature-level concatenation, leading to redundancy and suboptimal performance. Moreover, these models frequently lack effective integration with clinically relevant data and encounter challenges in integrating diverse scales and dimensions, as well as incorporating the liver background, which holds clinical significance but has been previously overlooked. Approach. To address these limitations, we propose two approaches. Firstly, we introduce the tensor fusion method to our model, which offers distinct advantages in handling multi-scale and multi-dimensional data fusion, potentially enhancing overall performance. Secondly, we pioneer the consideration of the liver background’s impact, integrating it into the feature extraction process using a deep learning segmentation-based algorithm. This innovative inclusion aligns the model more closely with real-world clinical scenarios, as the liver background may contain crucial information related to postoperative recurrence. Main results. We collected radiomics (MRI) and histopathological images from 176 cases diagnosed by experienced clinicians across two independent centers. Our proposed network underwent training and 5-fold cross-validation on this dataset before validation on an external test dataset comprising 40 cases. Ultimately, our model demonstrated outstanding performance in predicting early recurrence of HCC postoperatively, achieving an AUC of 0.883. Significance. These findings signify significant progress in addressing challenges related to multimodal data fusion and hold promise for more accurate clinical outcome predictions. In this study, we exploited global 3D liver background into modelling which is crucial to to the prognosis assessment and analyzed the whole liver background in addition to the tumor region. Both MRI images and histopathological images of HCC were fused at high-dimensional feature space using tensor techniques to solve cross-scale data integration issue.

Role of post‐hepatectomy portal hypertension in predicting the outcome of hepatocellular carcinoma after curative resection

AbstractAimsPortal venous pressure frequently increases after a major hepatectomy. We aimed to assess the outcomes of patients with hepatocellular carcinoma (HCC) with different post‐hepatectomy portal pressure statuses and the predictive factors correlated with prognosis and post‐hepatectomy portal hypertension (PHPH).MethodsData from consecutive patients who underwent curative‐intent hepatectomy for HCC at the Eastern Hepatobiliary Surgery Hospital and Mengchao Hepatobiliary Hospital of Fujian Medical University between January 2008 and December 2016 were retrospectively analyzed. Patients were followed up until March 1, 2022. PHPH was defined as new‐onset portal hypertension (PH) in patients without preoperative PH within 1 month of hepatectomy. Patients were classified into two groups according to the presence or absence of PHPH: non‐PH and PHPH. The clinicopathological characteristics were compared between the two groups. Univariate and multivariate analyses were used to identify independent risk factors for early and late recurrence of HCC, overall survival (OS), and PHPH.ResultsDisease‐free survival rates were significantly higher in the non‐PH group (n = 1068) than those in the PHPH group (n = 423) (62.0%, 39.0%, and 31.0% vs. 46.2%, 24.5%, and 19.3% at 1, 3, and 5 years, respectively; all p &lt; 0.001). The 1‐, 3‐, and 5‐year OS rates were 91.0%, 66.4%, and 51.4% in the non‐PH group and 80.0%, 48.9%, and 32.6% in the PHPH group, respectively (all p &lt; 0.001). Multivariate analysis revealed that PHPH was independently associated with early recurrence of HCC and poor OS (hazard ratio [HR] 1.476, 95% confidence interval [CI] 1.279–1.704, p &lt; 0.001 and HR 1.601, 95% CI 1.383–1.853, p &lt; 0.001, respectively). Furthermore, hepatitis B virus infection, cirrhosis, preoperative alanine aminotransferase &gt; 40 U/L, and major hepatectomy were identified as independent risk factors for PHPH.ConclusionsPHPH was associated with early recurrence of HCC and poor OS but not with late recurrence. Therefore, PHPH may be an attractive target for therapeutic interventions and follow‐up surveillance to improve prognosis.

Delta-radiomics Analysis Based on Multi-phase Contrast-enhanced MRI to Predict Early Recurrence in Hepatocellular Carcinoma After Percutaneous Thermal Ablation

Rationale and ObjectivesIt is critical to predict early recurrence (ER) after percutaneous thermal ablation (PTA) for hepatocellular carcinoma (HCC). We aimed to develop and validate a delta-radiomics nomogram based on multi-phase contrast-enhanced magnetic resonance imaging (MRI) to preoperatively predict ER of HCC after PTA. Materials and MethodsWe retrospectively enrolled 164 patients with HCC and divided them into training, temporal validation, and other-scanner validation cohorts (n=110, 29, and 25, respectively). The volumes of interest of the intratumoral and/or peritumoral regions were delineated on preoperative multi-phase MR images. Original radiomics features were extracted from each phase, and delta-radiomics features were calculated. Logistic regression was used to train the corresponding radiomics models. The clinical and radiological characteristics were evaluated and combined to establish a clinical-radiological model. A fusion model comprising the best radiomics scores and clinical-radiological risk factors was constructed and presented as a nomogram. The performance of each model was evaluated and recurrence-free survival (RFS) was assessed. ResultsChild-Pugh grade B, high-risk tumor location, and an incomplete/absent tumor capsule were independent predictors of ER. The optimal radiomics model comprised 12 delta-radiomics features with areas under the curve (AUCs) of 0.834, 0.795, and 0.769 in the training, temporal validation, and other-scanner validation cohorts, respectively. The nomogram showed the best predictive performance with AUCs as 0.893, 0.854, and 0.827 in the three datasets. There was a statistically significant difference in RFS between the risk groups calculated using the delta-radiomics model and nomogram. ConclusionsThe nomogram combined with the delta-radiomic score and clinical-radiological risk factors could non-invasively predict ER of HCC after PTA.

Impact of anatomical liver resection for hepatocellular carcinoma in preventing early-phase local recurrence after surgery.

The superiority of anatomical liver resection (AR) for localized hepatocellular carcinoma (HCC) over nonanatomical liver resection (NR) remains controversial. This study aimed to investigate the impact of AR in preventing local and early HCC recurrence. A total of 280 patients who underwent initial liver resection for solitary HCC ≤5 cm in diameter were categorized into the AR and NR groups and compared using propensity score matching analysis. Between the matched pairs (n = 87 in each group), the incidence rates of local and early (recurrence within 2 years after surgery) recurrences in the AR group were significantly lower than those in the NR group (13.8% vs. 28.7%, p = .025; 20.7% vs. 35.6%, p = .028, respectively). The overall survival in the AR group was better than that in the NR group (median: 13.4 vs. 7.6 years, p = .003). NR was among independent risk factors for early recurrence (odds ratio: 1.98, 95% CI: 1.1-3.6, p = .023) and prognostic factors for local recurrence (hazard ratio: 2.44, 95% CI: 1.4-4.4, p = .003). AR is superior in controlling local and early recurrence postoperatively for solitary HCC ≤5 cm in diameter compared with NR.

The role of adjuvant transcatheter arterial chemoembolization following repeated curative resection/ablation for hepatocellular carcinoma with early recurrence: a propensity score matching analysis

BackgroundThe role of adjuvant transcatheter arterial chemoembolization (TACE) following repeated resection/ablation for recurrent hepatocellular carcinoma (HCC) remains uncertain. The aim of this study was to assess the effectiveness of adjuvant TACE following repeated resection or ablation in patients with early recurrent HCC.MethodsInformation for patients who underwent repeated surgery or radiofrequency ablation (RFA) for early recurrent HCCs (< 2 years) at our institution from January 2017 to December 2020 were collected. Patients were divided into adjuvant TACE and observation groups according to whether they received adjuvant TACE or not. The recurrence-free survival (RFS) and overall survival (OS) were compared between the two groups before and after propensity score matching (PSM).ResultsOf the 225 patients enrolled, the median time of HCC recurrence was 11 months (IQR, 6–16 months). After repeated surgery or radiofrequency ablation (RFA) for recurrent tumors, 45 patients (20%) received adjuvant TACE while the remaining 180 (80%) didn’t. There were no significant differences in RFS (P = 0.325) and OS (P = 0.072) between adjuvant TACE and observation groups before PSM. There were also no significant differences in RFS (P = 0.897) and OS (P = 0.090) between the two groups after PSM. Multivariable analysis suggested that multiple tumors, liver cirrhosis, and RFA were independent risk factors for the re-recurrence of HCC.ConclusionAdjuvant TACE after repeated resection or ablation for early recurrent HCCs was not associated with a long-term survival benefit in this single-center cohort.

MRI radiomics based on deep learning automated segmentation to predict early recurrence of hepatocellular carcinoma.

To investigate the utility of deep learning (DL) automated segmentation-based MRI radiomic features and clinical-radiological characteristics in predicting early recurrence after curative resection of single hepatocellular carcinoma (HCC). This single-center, retrospective study included consecutive patients with surgically proven HCC who underwent contrast-enhanced MRI before curative hepatectomy from December 2009 to December 2021. Using 3D U-net-based DL algorithms, automated segmentation of the liver and HCC was performed on six MRI sequences. Radiomic features were extracted from the tumor, tumor border extensions (5 mm, 10 mm, and 20 mm), and the liver. A hybrid model incorporating the optimal radiomic signature and preoperative clinical-radiological characteristics was constructed via Cox regression analyses for early recurrence. Model discrimination was characterized with C-index and time-dependent area under the receiver operating curve (tdAUC) and compared with the widely-adopted BCLC and CNLC staging systems. Four hundred and thirty-four patients (median age, 52.0 years; 376 men) were included. Among all radiomic signatures, HCC with 5 mm tumor border extension and liver showed the optimal predictive performance (training set C-index, 0.696). By incorporating this radiomic signature, rim arterial phase hyperenhancement (APHE), and incomplete tumor "capsule," a hybrid model demonstrated a validation set C-index of 0.706 and superior 2-year tdAUC (0.743) than both the BCLC (0.550; p < 0.001) and CNLC (0.635; p = 0.032) systems. This model stratified patients into two prognostically distinct risk strata (both datasets p < 0.001). A preoperative imaging model incorporating the DL automated segmentation-based radiomic signature with rim APHE and incomplete tumor "capsule" accurately predicted early postsurgical recurrence of a single HCC. The DL automated segmentation-based MRI radiomic model with rim APHE and incomplete tumor "capsule" hold the potential to facilitate individualized risk estimation of postsurgical early recurrence in a single HCC. A hybrid model integrating MRI radiomic signature was constructed for early recurrence prediction of HCC. The hybrid model demonstrated superior 2-year AUC than the BCLC and CNLC systems. The model categorized the low-risk HCC group carried longer RFS.

Multiparametric MRI manifestations of the spontaneous intratumoral coagulative necrosis in HCC.

To investigate the MRI manifestations of the spontaneous intratumoral coagulative necrosis (iCN) in patients with hepatocellular carcinoma (HCC) and its value in predicting the postoperative early recurrence (≤ 2years). Patients with HCC who underwent preoperative multiparametric MRI between January 2015 and February 2019 were enrolled in this retrospective study. The MRI manifestations of iCNs on TIWI, T2WI, and ADC were recorded. The sensitivity and specificity of MRI for the detection of iCNs were also evaluated. A multivariable Cox proportional hazards model and the Kaplan-Meier method were used to verify the value of histologically-confirmed and MRI-identified iCNs, respectively, in predicting early recurrence. A total of 163 patients (median age, 56years; interquartile range, 49-64years; 139 men) with HCCs were evaluated, of whom 27(16.6%) had histologically-confirmed iCNs. MRI identified 92.6% (25 of 27; 95% confidence interval [CI] 74.2%, 98.7%) of iCNs (sensitivity), with a specificity of 79.4% (78 of 136; 95% CI 71.4%, 85.7%), based on non-enhancement on post-contrast MRI. And the MRI-identified iCNs were characterized by a similar appearance to surrounding tumour tissue shown on pre-contrast MRI but not enhanced on post-contrast MRI. The multivariable Cox proportional hazards model revealed that only the presence of histologically-confirmed iCN was independently associated with early HCC recurrence (hazard ratio = 2.73; 95% CI 1.20, 6.21; P = 0.017). The Kaplan-Meier curve showed that the presence of MRI-identified iCN was also associated with early recurrence (P < 0.001). Multiparametric MRI identified iCNs with high sensitivity and modest specificity. The presence of iCNs is associated with early HCC recurrence.

Novel immune classification based on machine learning of pathological images predicts early recurrence of hepatocellular carcinoma.

Immune infiltration within the tumor microenvironment (TME) plays a significant role in the onset and progression of hepatocellular carcinoma (HCC). Machine learning applied to pathological images offers a practical means to explore the TME at the cellular level. Our former research employed a transfer learning procedure to adapt a convolutional neural network (CNN) model for cell recognition, which could recognize tumor cells, lymphocytes, and stromal cells autonomously and accurately within the images. This study introduces a novel immune classification system based on the modified CNN model. Patients with HCC from both Beijing Hospital and The Cancer Genome Atlas (TCGA) database were included in this study. Additionally, least absolute shrinkage and selection operator (LASSO) analyses, along with logistic regression, were utilized to develop a prognostic model. We proposed an immune classification based on the percentage of lymphocytes, with a threshold set at the median lymphocyte percentage. Patients were categorized into high or low infiltration subtypes based on whether their lymphocyte percentages were above or below the median, respectively. Patients with different immune infiltration subtypes exhibited varying clinical features and distinct TME characteristics. The low-infiltration subtype showed a higher incidence of hypertension and fatty liver, more advanced tumor stages, downregulated immune-related genes, and higher infiltration of immunosuppressive cells. A reliable prognostic model for predicting early recurrence of HCC based on clinical features and immune classification was established. The area under the curve (AUC) of the receiver operating characteristic (ROC) curves was 0.918 and 0.814 for the training and test sets, respectively. In conclusion, we proposed a novel immune classification system based on cell information extracted from pathological slices, provides a novel tool for prognostic evaluation in HCC.

Preoperative prediction power of radiomics and non-radiomics methods based on MRI for early recurrence in hepatocellular carcinoma: a systemic review and meta-analysis.

To compare radiomics and non-radiomics in predicting early recurrence (ER) in patients with hepatocellular carcinoma (HCC) after curative surgery. We systematically searched PubMed and Embase databases. Studies with clear reference criteria were selected. Data were extracted and assessed for quality using the quality in prognosis studies tool (QUIPS)by two independent authors. All included radiomics studies underwent radiomics quality score (RQS) assessment. We calculated sensitivity, specificity, positive likelihood ratio (PLR), and negative likelihood ratio (NLR) using random or fixed models with a 95%CI. Forest maps visualized the data, and summary receiver operating characteristic (sROC) curves with the area under the curve (AUC) were generated. Meta-regression and subgroup analyses explored sources of heterogeneity. We compared sensitivity, specificity, PLR, and NLR using the z-test and compared AUC values using the Delong test. Our meta-analysis included 10 studies comprising 1857 patients. For radiomics, the pooled sensitivity, specificity, AUC of sROC, PLR and NLR were 0.84(95%CI: 0.78-0.89), 0.80(95%CI: 0.75-0.85), 0.89(95%CI: 0.86-0.91), 4.28(95%CI: 3.48-5.27) and 0.20(95%CI: 0.14-0.27), respectively, but with significant heterogeneity (I2 = 60.78% for sensitivity, I2 = 55.79% for specificity) and potential publication bias (P = 0.04). The pooled sensitivity, specificity, AUC of sROC, PLR, NLR for non-radiomics were 0.75(95%CI:0.68-0.81), 0.78(95%CI:0.72-0.83), 0.83(95%CI: 0.80-0.86), 3.45(95%CI: 2.68-4.44) and 0.32(95%CI: 0.24-0.41), respectively. There was no significant heterogeneity in this group (I2 = 0% for sensitivity, I2 = 17.27% for specificity). Radiomics showed higher diagnostic accuracy (AUC: 0.89 vs. 0.83, P = 0.0456), higher sensitivity (0.84 vs. 0.75, P = 0.0385) and lower NLR (0.20 vs. 0.32, P = 0.0287). The radiomics from preoperative MRI effectively predicts ER of HCC and has higher diagnostic accuracy than non-radiomics. Due to potential publication bias and suboptimal RQS scores in radiomics, these results should be interpreted cautiously.

Computed tomography-based radiomics to predict early recurrence of hepatocellular carcinoma post-hepatectomy in patients background on cirrhosis.

The prognosis for hepatocellular carcinoma (HCC) in the presence of cirrhosis is unfavourable, primarily attributable to the high incidence of recurrence. To develop a machine learning model for predicting early recurrence (ER) of post-hepatectomy HCC in patients with cirrhosis and to stratify patients' overall survival (OS) based on the predicted risk of recurrence. In this retrospective study, 214 HCC patients with cirrhosis who underwent curative hepatectomy were examined. Radiomics feature selection was conducted using the least absolute shrinkage and selection operator and recursive feature elimination methods. Clinical-radiologic features were selected through univariate and multivariate logistic regression analyses. Five machine learning methods were used for model comparison, aiming to identify the optimal model. The model's performance was evaluated using the receiver operating characteristic curve [area under the curve (AUC)], calibration, and decision curve analysis. Additionally, the Kaplan-Meier (K-M) curve was used to evaluate the stratification effect of the model on patient OS. Within this study, the most effective predictive performance for ER of post-hepatectomy HCC in the background of cirrhosis was demonstrated by a model that integrated radiomics features and clinical-radiologic features. In the training cohort, this model attained an AUC of 0.844, while in the validation cohort, it achieved a value of 0.790. The K-M curves illustrated that the combined model not only facilitated risk stratification but also exhibited significant discriminatory ability concerning patients' OS. The combined model, integrating both radiomics and clinical-radiologic characteristics, exhibited excellent performance in HCC with cirrhosis. The K-M curves assessing OS revealed statistically significant differences.

Pre-operative enhanced magnetic resonance imaging combined with clinical features predict early recurrence of hepatocellular carcinoma after radical resection.

Indentifying predictive factors for postoperative recurrence of hepatocellular carcinoma (HCC) has great significance for patient prognosis. To explore the value of gadolinium ethoxybenzyl diethylenetriamine pentaacetic acid (Gd-EOB-DTPA) enhanced magnetic resonance imaging (MRI) combined with clinical features in predicting early recurrence of HCC after resection. A total of 161 patients with pathologically confirmed HCC were enrolled. The patients were divided into early recurrence and non-early recurrence group based on the follow-up results. The clinical, laboratory, pathological results and Gd-EOB-DTPA enhanced MRI imaging features were analyzed. Of 161 patients, 73 had early recurrence and 88 were had non-early recurrence. Univariate analysis showed that patient age, gender, serum alpha-fetoprotein level, the Barcelona Clinic Liver Cancer stage, China liver cancer (CNLC) stage, microvascular invasion (MVI), pathological satellite focus, tumor size, tumor number, tumor boundary, tumor capsule, intratumoral necrosis, portal vein tumor thrombus, large vessel invasion, nonperipheral washout, peritumoral enhancement, hepatobiliary phase (HBP)/tumor signal intensity (SI)/peritumoral SI, HBP peritumoral low signal and peritumoral delay enhancement were significantly associated with early recurrence of HCC after operation. Multivariate logistic regression analysis showed that patient age, MVI, CNLC stage, tumor boundary and large vessel invasion were independent predictive factors. External data validation indicated that the area under the curve of the combined predictors was 0.861, suggesting that multivariate logistic regression was a reasonable predictive model for early recurrence of HCC. Gd-EOB-DTPA enhanced MRI combined with clinical features would help predicting the early recurrence of HCC after operation.