A Novel Online Calculator to Predict Risk of Microvascular Invasion in the Preoperative Setting for Hepatocellular Carcinoma Patients Undergoing Curative-Intent Surgery

Impact of an artificial intelligence based model to predict non-transplantable recurrence among patients with hepatocellular carcinoma

OBJECTIVE

We sought to develop Artificial Intelligence (AI) based models to predict non-transplantable recurrence (NTR) of hepatocellular carcinoma (HCC) following hepatic resection (HR).

METHODS

HCC patients who underwent HR between 2000-2020 were identified from a multi-institutional database. NTR was defined as recurrence beyond Milan Criteria. Different machine learning (ML) and deep learning (DL) techniques were used to develop and validate two prediction models for NTR, one using only preoperative factors and a second using both preoperative and postoperative factors.

RESULTS

Overall, 1763 HCC patients were included. Among 877 patients with recurrence, 364 (41.5%) patients developed NTR. An ensemble AI model demonstrated the highest area under ROC curves (AUC) of 0.751 (95% CI: 0.719-0.782) and 0.717 (95% CI:0.653-0.782) in the training and testing cohorts, respectively which improved to 0.858 (95% CI: 0.835-0.884) and 0.764 (95% CI: 0.704-0.826), respectively after incorporation of postoperative pathologic factors. Radiologic tumor burden score and pathological microvascular invasion were the most important preoperative and postoperative factors, respectively to predict NTR. Patients predicted to develop NTR had overall 1- and 5-year survival of 75.6% and 28.2%, versus 93.4% and 55.9%, respectively, among patients predicted to not develop NTR (p < 0.0001).

CONCLUSION

The AI preoperative model may help inform decision of HR versus LT for HCC, while the combined AI model can frame individualized postoperative care (https://altaf-pawlik-hcc-ntr-calculator.streamlit.app/).

Machine learning models including preoperative and postoperative albumin-bilirubin score: short-term outcomes among patients with hepatocellular carcinoma

BACKGROUND

We sought to assess the impact of various perioperative factors on the risk of severe complications and post-surgical mortality using a novel maching learning technique.

METHODS

Data on patients undergoing resection for HCC were obtained from an international, multi-institutional database between 2000 and 2020. Gradient boosted trees were utilized to construct predictive models.

RESULTS

Among 962 patients who underwent HCC resection, the incidence of severe postoperative complications was 12.7% (n = 122); in-hospital mortality was 2.9% (n = 28). Models that exclusively used preoperative data achieved AUC values of 0.89 (95%CI 0.85 to 0.92) and 0.90 (95%CI 0.84 to 0.96) to predict severe complications and mortality, respectively. Models that combined preoperative and postoperative data achieved AUC values of 0.93 (95%CI 0.91 to 0.96) and 0.92 (95%CI 0.86 to 0.97) for severe morbidity and mortality, respectively. The SHAP algorithm demonstrated that the factor most strongly predictive of severe morbidity and mortality was postoperative day 1 and 3 albumin-bilirubin (ALBI) scores.

CONCLUSION

Incorporation of perioperative data including ALBI scores using ML techniques can help risk-stratify patients undergoing resection of HCC.

A preoperative model to predict overall survival in patients with hepatoma undergoing resection

BACKGROUND

We aimed to develop a preoperative model to predict overall survival (OS) in patients with hepatoma undergoing liver resection (LR).

METHODS

Patients who underwent LR for Barcelona Clinic Liver Cancer (BCLC) stage 0, A, or B hepatoma were enrolled. Tumor burden score (TBS) scores were determined using the following equation: TBS (Pinna et al., 2018) 2 = (largest tumor size [in cm])(Pinna et al., 2018) 2 ​+ ​(tumor number) (Pinna et al., 2018) 22. The cutoff values for radiographic TBS were based on our recently published paper: low, <2.6; medium, 2.6-7.9; high, >7.9.

RESULTS

Multivariate analysis showed that radiographic TBS (low: referent; medium: HR ​= ​2.89; 95 ​% CI: 1.60-5.21; p ​< ​0.001; high, HR ​= ​7.60; 95 ​% CI: 3.80-15.2; p ​< ​0.001), AFP (<400 ​ng/mL: referent; ≧400 ​ng/mL: HR ​= ​1.67, 95 ​% CI: 1.11-2.52, p ​= ​0.014), and cirrhosis (absence: referent; presence: HR ​= ​1.88, 95 ​% CI: 1.30-2.72, p ​< ​0.001) were associated with OS. A simplified risk score was superior to BCLC system in concordance index (0.688 vs. 0.623).

CONCLUSIONS

We have developed a preoperative model that performs better in predicting OS than the BCLC system.

Role of microvascular invasion in early recurrence of hepatocellular carcinoma after liver resection: A literature review

Hepatectomy is widely considered a potential treatment for hepatocellular carcinoma (HCC). Unfortunately, one-third of HCC patients have tumor recurrence within 2 years after surgery (early recurrence), accounting for more than 60% of all recurrence patients. Early recurrence is associated with a worse prognosis. Previous studies have shown that microvascular invasion (MVI) is one of the key factors for early recurrence and poor prognosis in patients with HCC after surgery. This paper reviews the latest literature and summarizes the predictors of MVI, the correlation between MVI and early recurrence, the identification of suspicious nodules or subclinical lesions, and the treatment strategies for MVI-positive HCC. The aim is to explore the management of patients with MVI-positive HCC.

Using the hazard function to evaluate hepatocellular carcinoma recurrence risk after curative resection

Predicting recurrence patterns of hepatocellular carcinoma (HCC) can be helpful in developing surveillance strategies. This study aimed to use the hazard function to investigate recurrence hazard and peak recurrence time transitions in patients with HCC undergoing liver resection (LR). We enrolled 1204 patients with HCC undergoing LR between 2007 and 2018 at our institution. Recurrence hazard, patterns, and peak rates were analyzed. The overall recurrence hazard peaked at 7.2 months (peak hazard rate [pHR]: 0.0197), but varied markedly. In subgroups analysis based on recurrence risk factors, patients with a high radiographic tumor burden score (pHR: 0.0521), alpha-fetoprotein level ≥ 400 ng/ml (pHR: 0.0427), and pT3-4 (pHR: 0.0656) showed a pronounced peak within the first year after LR. Patients with cirrhosis showed a pronounced peak within three years after LR (pHR: 0.0248), whereas those with Barcelona Clinic Liver Cancer stage B (pHR: 0.0609) and poor tumor differentiation (pHR: 0.0451) showed multiple peaks during the 5-year follow-up period. In contrast, patients without these recurrence risk factors had a relatively flat hazard function curve. HCC recurrence hazard, patterns, and peak rates varied substantially depending on different risk factors of HCC recurrence.

Development of a Model including MRI Features for Predicting Advanced-stage Recurrence of Hepatocellular Carcinoma after Liver Resection

Background Identifying patients at high risk for advanced-stage hepatocellular carcinoma (HCC) recurrence after liver resection may improve patient survival. Purpose To develop a model including MRI features for predicting postoperative advanced-stage HCC recurrence. Materials and Methods This single-center, retrospective study includes consecutive adult patients who underwent preoperative contrast-enhanced MRI and curative-intent resection for early- to intermediate-stage HCC (from December 2011 to April 2021). Three radiologists evaluated 52 qualitative features on MRI scans. In the training set, Fine-Gray proportional subdistribution hazard analysis was performed to identify clinical, laboratory, imaging, pathologic, and surgical variables to include in the predictive model. In the test set, the concordance index (C-index) was computed to compare the developed model with current staging systems. The Kaplan-Meier survival curves were compared using the log-rank test. Results The study included 532 patients (median age, 54 years; IQR, 46-62 years; 465 male patients), 302 patients from the training set (median age, 54 years; IQR, 46-63 years; 265 male patients), and 128 patients from the test set (median age, 53 years; IQR, 46-63 years; 108 male patients). Advanced-stage recurrence was observed in 38 of 302 (12.6%) and 15 of 128 (11.7%) of patients from the training and test sets, respectively. Serum neutrophil count (109/L), tumor size (in centimeters), and arterial phase hyperenhancement proportion on MRI scans were associated with advanced-stage recurrence (subdistribution hazard ratio range, 1.16-3.83; 95% CI: 1.02, 7.52; P value range, <.001 to .02) and included in the predictive model. The model showed better test set prediction for advanced-stage recurrence than four staging systems (2-year C-indexes, 0.82 [95% CI: 0.74, 0.91] vs 0.63-0.68 [95% CI: 0.52, 0.82]; P value range, .001-.03). Patients at high risk for HCC recurrence (model score, ≥15 points) showed increased advanced-stage recurrence and worse all-stage recurrence-free survival (RFS), advanced-stage RFS, and overall survival than patients at low risk for HCC recurrence (P value range, <.001 to .02). Conclusion A model combining serum neutrophil count, tumor size, and arterial phase hyperenhancement proportion predicted advanced-stage HCC recurrence better than current staging systems and may identify patients at high risk. Published under a CC BY 4.0 license. Supplemental material is available for this article. See also the editorial by Tsai and Mellnick in this issue.

Preoperative prediction and risk assessment of microvascular invasion in hepatocellular carcinoma

Hepatocellular carcinoma (HCC) is one of the most common and highly lethal tumors worldwide. Microvascular invasion (MVI) is a significant risk factor for recurrence and poor prognosis after surgical resection for HCC patients. Accurately predicting the status of MVI preoperatively is critical for clinicians to select treatment modalities and improve overall survival. However, MVI can only be diagnosed by pathological analysis of postoperative specimens. Currently, numerous indicators in serology (including liquid biopsies) and imaging have been identified to effective in predicting the occurrence of MVI, and the multi-indicator model based on deep learning greatly improves accuracy of prediction. Moreover, several genes and proteins have been identified as risk factors that are strictly associated with the occurrence of MVI. Therefore, this review evaluates various predictors and risk factors, and provides guidance for subsequent efforts to explore more accurate predictive methods and to facilitate the conversion of risk factors into reliable predictors.

Identifying Proliferative Hepatocellular Carcinoma at Pretreatment CT: Implications for Therapeutic Outcomes after Transarterial Chemoembolization

Background Hepatocellular carcinomas (HCCs) can be divided into proliferative and nonproliferative types, which may have implications for outcomes after conventional transarterial chemoembolization (cTACE). Biopsy to identify proliferative HCC is not routinely performed before cTACE. Purpose To develop and validate a predictive model for identifying proliferative HCCs using CT imaging features and to compare therapeutic outcomes between predicted proliferative and nonproliferative HCCs after cTACE according to this model. Materials and Methods This retrospective multicenter study included adults with HCC who underwent liver resection or cTACE between August 2013 and December 2020. A CT-based predictive model for identifying proliferative HCCs was developed and externally validated in a cohort that underwent resection. Diagnostic performance was calculated for the model. Thereafter, patients in the cTACE cohort were stratified into groups with predicted proliferative or nonproliferative HCCs according to the model. The primary outcome was overall survival (OS), and the secondary outcomes were tumor response rate and progression-free survival (PFS). These were compared between the two groups with use of the χ2 test and the log-rank test. Results A total of 1194 patients (1021 men; mean age, 54 years ± 12 [SD]; median follow-up time, 29.1 months) were included. The predictive model, named the SMARS score, incorporated lobulated shape, mosaic architecture, α-fetoprotein levels, rim arterial phase hyperenhancement, and satellite lesions. The area under the receiver operating characteristic curve for the SMARS score was 0.83 for the training cohort and 0.80 for the validation cohort. According to the SMARS score, patients with predicted proliferative HCCs (n = 114) had lower tumor response rate (48% vs 71%; P < .001) and worse PFS (6.6 months vs 12.4 months; P < .001) and OS (14.4 months vs 38.7 months; P < .001) than those with nonproliferative HCCs (n = 263). Conclusion The predictive model demonstrated good performance for identifying proliferative HCCs. According to the SMARS score, patients with predicted proliferative HCCs have worse prognosis than those with predicted nonproliferative HCCs after cTACE. © RSNA, 2023 Supplemental material is available for this article.

TBS-Based Preoperative Score to Predict Non-transplantable Recurrence and Identify Candidates for Upfront Resection Versus Transplantation for Hepatocellular Carcinoma

BACKGROUND

Recurrence following liver resection (LR) for hepatocellular carcinoma (HCC) can be as high as 50-70%. While salvage liver transplantation may be feasible, patients may develop a non-transplantable recurrence (NTR) (recurrence beyond Milan criteria). We sought to identify preoperative risk factors to predict NTR after resection.

PATIENTS AND METHODS

Patients who underwent curative-intent LR for HCC were identified from a multi-institutional database. Preoperative factors associated with NTR were identified and a risk score model (NTR score) was developed and validated.

RESULTS

Among 1620 patients, 842 (52.0%) developed recurrence; among patients with recurrence, NTR occurred in 341 (40.5%) with a median recurrence-free survival (RFS) of 30 months (24.7-35.3 months). On multivariable analysis, factors associated with NTR included alpha fetoprotein (AFP) > 400 ng/mL [hazard ratio (HR) 1.71, 95% confidence interval (CI) 1.33-2.19], albumin-bilirubin grade (ALBI) (referent low, medium ALBI: HR 1.41, 95% CI 1.10-1.81, high ALBI: HR 2.47, 95% CI 0.91-6.68), and tumor burden score (TBS) (referent low, high TBS: HR 2.55, 95% CI, 1.99-3.28). A simplified TBS-based NTR score was developed using the β-coefficients of each factor (C-index 0.68, 95% CI 0.65-0.71). Higher NTR score was associated with incrementally worse 5-year RFS (low 44.8%, medium 37.5%, high 24.5%) [area under the curve (AUC) 0.59] and increased incidence of NTR (low 13.7%, medium 25.4%, high 38.2%) (AUC 0.65) (both p < 0.001). Moreover, higher NTR score was associated with higher risk of extrahepatic recurrence (low 11.3%, medium 28.8%, high 37.5%) (p < 0.001).

CONCLUSION

NTR following curative-intent resection of HCC occurred in one in five patients. A simple TBS-based NTR score accurately predicted the risk of NTR and may help identify candidates for upfront resection versus transplantation.

Alpha-Fetoprotein Combined with Radiographic Tumor Burden Score to Predict Overall Survival after Liver Resection in Hepatocellular Carcinoma

We evaluated whether combining the radiographic tumor burden score (TBS) and alpha-fetoprotein (AFP) level could be used to stratify overall survival (OS) among hepatocellular carcinoma (HCC) patients after liver resection (LR). Patients who underwent LR for Barcelona Clinic Liver Cancer stage 0, A, or B HCC between 2011 and 2018 were enrolled. TBS scores were calculated using the following equation: TBS² = (largest tumor size (in cm))² + (tumor number)². Among 743 patients, 193 (26.0%) patients had a low TBS (<2.6), 474 (63.8%) had a moderate TBS (2.6-7.9), and 75 (10.1%) had a high TBS (>7.9). Those with a TBS ≤ 7.9 and AFP < 400 ng/mL had a significantly better OS than those with a TBS > 7.9 and an AFP < 400 ng/mL (p = 0.003) or ≥ 400 ng/mL (p < 0.001). A multivariate analysis using TBS ≤ 7.9 and AFP < 400 ng/mL as the reference values showed that a TBS > 7.9 and an AFP < 400 ng/mL (hazard ratio (HR): 2.063; 95% confidence interval [CI]: 1.175-3.623; p = 0.012) or ≥ 400 ng/mL (HR: 6.570; 95% CI: 3.684-11.719; p < 0.001) were independent predictors of OS. In conclusion, combining radiographic TBSs and AFP levels could stratify OS among HCC patients undergoing LR.