Hepatocellular carcinoma (HCC) is characterized by a high mortality rate. The Liver Imaging Reporting and Data System (LI-RADS) results in a considerable number of indeterminate observations, rendering an accurate diagnosis difficult.

We developed four deep learning models for diagnosing HCC on computed tomography (CT) via a training-validation-testing approach. Thin-slice triphasic CT liver images and relevant clinical information were collected and processed for deep learning. HCC was diagnosed and verified via a 12-month clinical composite reference standard. CT observations among at-risk patients were annotated using LI-RADS. Diagnostic performance was assessed by internal validation and independent external testing. We conducted sensitivity analyses of different subgroups, deep learning explainability evaluation, and misclassification analysis.

From 2,832 patients and 4,305 CT observations, the best-performing model was Spatio-Temporal 3D Convolution Network (ST3DCN), achieving area under receiver-operating-characteristic curves (AUCs) of 0.919 (95% CI, 0.903-0.935) and 0.901 (95% CI, 0.879-0.924) at the observation (n = 1,077) and patient (n = 685) levels, respectively during internal validation, compared with 0.839 (95% CI, 0.814-0.864) and 0.822 (95% CI, 0.790-0.853), respectively for standard of care radiological interpretation. The negative predictive values of ST3DCN were 0.966 (95% CI, 0.954-0.979) and 0.951 (95% CI, 0.931-0.971), respectively. The observation-level AUCs among at-risk patients, 2-5-cm observations, and singular portovenous phase analysis of ST3DCN were 0.899 (95% CI, 0.874-0.924), 0.872 (95% CI, 0.838-0.909) and 0.912 (95% CI, 0.895-0.929), respectively. In external testing (551/717 patients/observations), the AUC of ST3DCN was 0.901 (95% CI, 0.877-0.924), which was non-inferior to radiological interpretation (AUC 0.900; 95% CI, 0.877--923).

ST3DCN achieved strong, robust performance for accurate HCC diagnosis on CT. Thus, deep learning can expedite and improve the process of diagnosing HCC.

The clinical applicability of deep learning in HCC diagnosis is potentially huge, especially considering the expected increase in the incidence and mortality of HCC worldwide. Early diagnosis through deep learning can lead to earlier definitive management, particularly for at-risk patients. The model can be broadly deployed for patients undergoing a triphasic contrast CT scan of the liver to reduce the currently high mortality rate of HCC.

Aim: The present study aimed to compare the long-term survival outcomes of hepatic resection (HR) and radiofrequency ablation (RFA) in patients with single small (≤2 cm) hepatocellular carcinoma (HCC).Materials & methods: This retrospective study enrolled patients with a single small HCC measuring 2 cm or smaller underwent HR or RFA as their initial treatment.Results: Overall survival (OS) was significantly higher in the HR group than in the RFA group, while no significant difference was observed in recurrence free survival (RFS) between the two groups. However, after propensity score matching, both OS and RFS in the HR group were significantly higher than in the RFA group. Multivariate analysis showed that patients with hepatitis B virus infection, elevated prothrombin-induced by vitamin K absence or antagonist-II, and albumin-bilirubin (ALBI) grade 2/3 before treatment had poorer OS. Patients with ALBI grade 1 in the HR group demonstrated the highest OS.Conclusion: HR showed significantly better long-term OS and RFS compared with RFA in patients with as a single HCC (≤2 cm). Moreover, the ALBI grade may help identify patients who would benefit from HR or RFA.

To examine the relationship between microvascular invasion (MVI) grading severity and long-term outcomes in early-stage hepatocellular carcinoma (HCC) patients undergoing laparoscopic liver resection (LLR).

Patients who had LLR for early-stage HCC were enrolled. According to the grading severity of MVI, patients were classified into M0, M1 and M2. Recurrence-free survival (RFS) and overall survival (OS) among the groups were compared. Univariate and multivariate Cox regression analyses were performed to identify independent risk factors of OS and RFS.

Among 233 patients, MVI grading as M0, M1, and M2 accounts for 122 (52.4 ​%), 84 (36 ​%), and 27 (11.6 ​%) patients, respectively. The median OS and RFS in patients with M0, M1, and M2 were 84.9, 40.1, and 25.2 months; and 76.9, 27.0, and 18.8 months, respectively. Multivariable analyses identified both M1 and M2 to be independent risk factors for OS and RFS.

Grading severity of MVI was independently associated with RFS and OS after LLR for early-stage HCC. Patients with MVI, especially those with M2, should receive stringent recurrence surveillance and active adjuvant therapy.

Liver resection and ablation remain the most common therapeutic options for Barcelona Clinic Liver Cancer (BCLC) stage 0-A hepatocellular carcinoma (HCC), but there is a lack of evidence to show which is the most suitable therapy. This study aimed to make concurrent multi-arm comparisons of the short-term and long-term outcomes of percutaneous ablation (PA), open (OLR) or laparoscopic liver resection (LLR) for these patients.

This was a retrospective observational cohort study. A series of generalized propensity score methods for multiple treatment groups were performed to concurrently compare the clinical outcomes of these three treatment options to balance potential confounders. Regression standardization was used to account for hazard of all-cause mortality and recurrence of intergroup differences.

Of the 1778 patients included, 1237, 307 and 234 underwent OLR, LLR and PA, respectively. After overlap weighting, which was the optimal adjustment strategy, patients in the minimally invasive group (LLR and PA groups) had few postoperative complications and short postoperative hospital stays (both P < 0.001). The 5-year recurrence-free survival (RFS) rate and 5-year overall survival (OS) rate were significantly higher in the LLR group when compared with the OLR and PA groups (RFS: 55.6% vs 48.0% vs 30.2%, P < 0.001; OS: 89.1% vs 79.7% vs 84.0%, P = 0.020). Multivariable Cox analysis and regression standardization showed that LLR was an independent factor for better RFS when compared with OLR and PA. In subgroup analysis, the long-term outcomes of patients with BCLC stage A HCC were consistent with the whole population.

In the observational study using various covariate adjustment analysis with excellent balance, LLR is not only minimally invasive, but also provides better RFS and equivalent OS for patients with BCLC stage 0-A HCC when compared with OLR and PA.

Late recurrence of hepatocellular carcinoma after curative resection significantly influences long-term patient survival outcomes, and yet it remains understudied. This study aims to explore the risk factors and patterns of late recurrence and predictors of subsequent outcome.

This single-center retrospective study analyzed 1,701 consecutive patients who achieved a disease-free survival period exceeding 2 years after curative resection for hepatocellular carcinoma between 2001 and 2018. Univariate and multivariate analyses of factors associated with late recurrence and death after recurrence were conducted using Cox's models.

The mean age of patients was 60.2 years, with 76.8% being male. During a median follow-up of 8.1 years, 653 patients (38.4%) experienced late recurrence, with median time to recurrence being 4.0 years (interquartile range, 2.7-6.0). Factors such as age >60, chronic hepatitis C, cirrhosis, high albumin-bilirubin grade, absence of family history, multiple tumors, satellite nodules, alpha-fetoprotein levels <400 ng/mL, and minor hepatic resection were identified as risk factors for late recurrence. Among patients with late recurrence, 131 (20.1%) underwent surgical treatment, 272 (41.7%) received radiofrequency ablation, and 27 (4.1%) exhibited extrahepatic lesions. A higher-high albumin-bilirubin grade, recurrent tumor >3 cm, and nonsurgical treatment emerged as predictors of death after late recurrence.

Over one-third of patients who remain disease-free for more than 2 years postresection will experience late recurrence during subsequent follow-up. For 2-year disease-free survivors, risk factors for late recurrence differ from early recurrence. Treating underlying hepatitis is of paramount importance, given its association with both the risk of late recurrence and survival outcomes post-recurrence.

Although 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 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.

A 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.

The 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.

Most patients with hepatocellular carcinoma (HCC) have a poor prognosis. Hepatectomy and local ablation are the main curative treatments for HCC. Nevertheless, the recurrence rate after hepatectomy or ablation is up to 70%, which seriously affects patient prognosis. Several adjuvant therapies have been explored to reduce postoperative recurrence. However, although a variety of adjuvant therapies have been shown to reduce the recurrence rate and improve overall survival, a standard consensus of national HCC guidelines for adjuvant treatment is lacking. Therefore, there are significant differences in the recommendations for adjuvant therapy for HCC between the Eastern and Western guidelines. A variety of adjuvant treatment methods, such as antiviral therapy, transarterial chemoembolization or traditional Chinese medicine, are recommended by the Chinese HCC guidelines. However, Western guidelines make few recommendations other than antiviral therapy. Adjuvant immune checkpoint inhibitors are recommended only in the recently updated American Association for the Study of Liver Diseases guidelines. This review summarized the existing adjuvant therapy options after curative hepatectomy or ablation and discusses several important dilemmas of adjuvant treatments.

We aimed to develop a Transformer-based deep learning (DL) network for prognostic stratification in hepatocellular carcinoma (HCC) patients undergoing RFA.

A Swin Transformer DL network was trained to establish associations between magnetic resonance imaging (MRI) datasets and the ground truth of microvascular invasion (MVI) based on 696 surgical resection (SR) patients with solitary HCC ≤3 cm, and was validated in an external cohort (n = 180). The multiphase MRI-based DL risk outputs using an optimal threshold of .5 was employed as a MVI classifier for prognosis stratification in the RFA cohort (n = 180).

Over 90% of all enrolled patients exhibited hepatitis B virus infection. Liver cirrhosis was significantly more prevalent in the RFA cohort compared to the SR cohort (72.2% vs. 44.1%, p < .001). The MVI risk outputs exhibited good performance (area under the curve values = .938 and .883) for predicting MVI in the training and validation cohort, respectively. The RFA patients at high risk of MVI classified by the MVI classifier demonstrated significantly lower recurrence-free survival (RFS) and overall survival rates at 1, 3 and 5 years compared to those classified as low risk (p < .001). Multivariate cox regression modelling of a-fetoprotein > 20 ng/mL [hazard ratio (HR) = 1.53; 95% confidence interval (95% CI): 1.02-2.33, p = .047], high risk of MVI (HR = 3.76; 95% CI: 2.40-5.88, p < .001) and unfavourable tumour location (HR = 2.15; 95% CI: 1.40-3.29, p = .001) yielded a c-index of .731 (bootstrapped 95% CI: .667-.778) for evaluating RFS after RFA. Among the three risk factors, MVI was the most powerful predictor for intrahepatic distance recurrence.

The proposed MVI classifier can serve as a valuable imaging biomarker for prognostic stratification in early-stage HCC patients undergoing RFA.

The impact of hepatic resection type on long-term oncological prognosis of patients with early-stage hepatocellular carcinoma (HCC) has not been systematically investigated. We sought to determine risk factors, recurrence patterns, and survival outcomes after anatomical resection (AR) versus non-anatomical resection (NAR) for early-stage HCC.

From a prospectively collected multicenter database, consecutive patients undergoing curative hepatectomy for early-stage HCC were identified. Recurrence patterns, overall survival (OS), recurrence-free survival (RFS), and risk factors were investigated in patients undergoing AR versus NAR using propensity score matching (PSM), subgroup analysis, and COX regression analysis.

A total of 3585 patients with early-stage HCC were enrolled, including 1287 and 2298 in the AR and NAR groups, respectively. After PSM, the OS and RFS of patients in the AR group were 58.8% and 42.7%, which were higher than those in the NAR group (52.2% and 30.6%, both p < 0.01). The benefits of AR were consistent across most subgroup analyses of OS and RFS. Multivariable COX regression analysis showed that AR was independently associated with better OS and RFS. Notably, although recurrence patterns were comparable, the risk factors for recurrence were not identical for AR versus NAR. Microvascular invasion and narrow resection margin were only associated with a higher recurrence rate after NAR.

This study demonstrated that AR decreases the risk of tumor recurrence and improves OS and RFS in patients with early-stage HCC. AR should be adopted as long as such a surgical maneuver is feasible for initial treatment of early-stage HCC.

The optimal treatment strategy for early-stage hepatocellular carcinoma (HCC) remains controversial, specifically in regard to surgical resection (SR) and ablation. The aim of this study was to investigate the impact of SR and ablation on recurrence and prognosis in early-stage HCC patients, to optimize treatment strategies and improve long-term survival.

A retrospective analysis was conducted on 801 patients diagnosed with Barcelona Clinic Liver Cancer (BCLC) stage 0/A HCC and treated with SR or ablation between January 2015 and December 2019. The effectiveness and complications of both treatments were analyzed, and patients were followed up to measure recurrence and survival. Propensity score matching (PSM) was employed to increase comparability between the two groups. The Kaplan-Meier method was used to analyze recurrence and survival, and a Cox risk proportional hazard model was used to identify risk factors that affect recurrence and surviva.

Before PSM, the overall survival (OS) rates were similar in both groups, with recurrence-free survival (RFS) rates better in the SR group than in the ablation group. After PSM, there was no significant difference in OS between the two groups. However, the RFS rates were significantly better in the SR group than in the ablation group. The ablation group exhibited superior outcomes compared to the SR group, with shorter treatment times, reduced bleeding, shorter hospital stays, and lower hospital costs. Concerning the location of the HCC within the liver, comparable efficacy was observed between SR and ablation for disease located in the noncentral region or left lobe. However, for HCCs located in the central region or right lobe of the liver, SR was more effective than ablation.

This study revealed no significant difference in OS between SR and ablation for early-stage HCC, with SR providing better RFS and ablation demonstrating better safety profiles and lower hospital costs. These findings offer valuable insights for clinicians in determining optimal treatment strategies for early-stage HCC patients, particularly in terms of balancing efficacy, safety, and cost considerations.

Approximately 50%-70% of patients with hepatocellular carcinoma experience recurrence within five years after curative hepatic resection or ablation. As a result, many patients receive adjuvant therapy after curative resection or ablation in order to prolong recurrence-free survival. The therapy recommended by national guidelines can differ, and guidelines do not specify when to initiate adjuvant therapy or how long to continue it. These and other unanswered questions around adjuvant therapies make it difficult to optimize them and determine which may be more appropriate for a given type of patient. These questions need to be addressed by clinicians and researchers.

Worldwide, hepatocellular carcinoma (HCC) is the third most common cause of cancer-related death. The remarkable improvements in treating HCC achieved in the last years have increased the complexity of HCC management. Following the need to have updated guidelines on the multidisciplinary treatment management of HCC, the Italian Scientific Societies involved in the management of this cancer have promoted the drafting of a new dedicated document. This document was drawn up according to the GRADE methodology needed to produce guidelines based on evidence. Here is presented the first part of guidelines, focused on the multidisciplinary tumor board of experts and surgical treatments of HCC.

RATIONALE AND OBJECTIVES: This meta-analysis was aimed at evaluating the predictive value of radiomics in the context of transarterial chemoembolization (TACE) therapeutic response (TR) for hepatocellular carcinoma (HCC) and patients' survival status (SS) and providing favorable evidence for clinical application.

We searched for literature in which radiomics was applied to assess the TR of TACE for HCC and the affected patients' survival status across PubMed, Embase, Cochrane Library and Web of Science until Jul 12, 2023. The quality of included literature was evaluated using a radiomics quality score (RQS) approach, and a meta-analysis was conducted using Stata15.0.

Twenty-four studies were included in the analysis. The meta-analysis revealed that the overall concordance-index (C-index) based on radiomics for predicting the TR and SS with TACE was 0.85 and 0.78, respectively. The combined radiomics-clinical model provided the best performance in evaluating the TR and SS associated with TACE. The C-index was 0.93 and 0.88 for TR and 0.84 and 0.80 for SS, in the training and validation sets, respectively. These values were higher than the 0.87 and 0.79 for TR and 0.79 and 0.70 for SS, respectively with the radiomics model, and 0.71 and 0.66 for TR and 0.72 and 0.66 for SS, respectively with the clinical model.

The radiomics prediction model for the efficacy of TACE in HCC showed a satisfactory prediction performance. The combined radiomics-clinic prediction model had the best performance.

To evaluate technical and clinical outcomes of intraoperative (laparoscopic/laparotomic) microwave ablation on HCC.

This is a retrospective single-center study evaluating consecutive patients treated for very early/early-stage HCC with intraoperative microwave ablation from 1 July 2017 to 30 June 2023. In these patients, a percutaneous US-guided approach was excluded due to the nodule's suboptimal visibility or harmful location and liver resection for a deep position or adherences. Data about the clinical stage, surgical approach, liver pathology and nodules characteristics, technical success, complications, and follow-up were collected. Technical success was intended as the absence of locoregional persistence at follow-up CT/MRI controls.

A total of 36 cirrhotic patients (M:F = 30:6, median age 67 years) were enrolled; 18/36 (50%) had a single nodule, 13/36 (36%) had two, 4/36 had three (11%), and 1/36 had four (3%). Among the patients, 24 (67%) were treated with laparoscopy, and 12/36 (33%) with a laparotomic approach. Sixty HCCs of 16.5 mm (6-50 mm) were treated for 7 min (2-30 min) with 100 W of power. A total of 55 nodules (92%) were treated successfully and showed no residual enhancement at the first postoperative follow-up; the other 5/60 (8%) underwent chemo/radioembolization. There was one complication (3%): a biliary fistula treated with percutaneous drainage and glue embolization. The average hospital stay was 3.5 days (1-51 days), and patients were followed up on average for 238 days (13-1792 days). During follow-up, 5/36 patients (14%) underwent liver transplantation, 1/36 (2%) died during hospitalization and 1 after discharge.

Laparoscopic/laparotomic intraoperative HCC MW ablation is feasible in patients unsuitable for percutaneous approach or hepatic resection, with rare complications and with good technical and clinical outcomes.