Predictive models and early postoperative recurrence evaluation for hepatocellular carcinoma based on gadoxetic acid-enhanced MR imaging

Abstract

Background The prognosis of hepatocellular carcinoma (HCC) is still poor largely due to the high incidence of recurrence. We aimed to develop and validate predictive models of early postoperative recurrence for HCC using clinical and gadoxetic acid-enhanced magnetic resonance (MR) imaging-based findings. Methods In this retrospective case-control study, 209 HCC patients, who underwent gadoxetic acid-enhanced MR imaging before curative-intent resection, were enrolled. Boruta algorithm and backward stepwise selection with Akaike information criterion (AIC) were used for variables selection Random forest, Gradient-Boosted decision tree and logistic regression model analysis were used for model development. The area under the receiver operating characteristic curve (AUC), calibration plots, and decision curve analysis were used to evaluate model’s performance. Results One random forest model with Boruta algorithm (RF-Boruta) was developed consisting of preoperative serum ALT and AFP levels and six MRI findings, while preoperative serum AST and AFP levels and four MRI findings were included in one logistic regression model with backward stepwise selection method (Logistic-AIC).The two predictive models demonstrated good discrimination performance in both the training set (RF-Boruta: AUC, 0.820; Logistic-AIC: AUC, 0.853), internal validation set (RF-Boruta: AUC, 0.857, Logistic-AIC: AUC, 0.812) and external validation set(RF-Boruta: AUC, 0.805, Logistic-AIC: AUC, 0.789). Besides, in both the internal validation and external validation sets, the RF-Boruta model outperformed Barcelona Clinic Liver Cancer (BCLC) stage (p < 0.05). Conclusions The RF-Boruta and Logistic-AIC models with good prediction performance for early postoperative recurrence may lead to optimal and comprehensive treatment approaches, and further improve the prognosis of HCC after resection.

Revolutionising hepatocellular carcinoma surveillance: Harnessing contrast-enhanced ultrasound and serological indicators for postoperative early recurrence prediction

“…For high-risk patients with recurrence, aggressive perioperative treatments such as immunotherapy, targeted therapy, and TACE might improve treatment outcomes. [18][19][20] Several noninvasive diagnostic methods have been used to predict early recurrence, including CT, [25] MRI, [26] positron emission tomography, [27] tumor genetic testing, [28] and serological markers. [29] Ultrasound is a routine procedure for liver assessment and is widely used in clinical practice.…”

Clinical-Radiological Characteristic for Predicting Ultra-Early Recurrence After Liver Resection in Solitary Hepatocellular Carcinoma Patients

“… 26 , 27 Additionally, the presence of satellite nodules has been reported to be independently associated with poor long-term survival and adverse prognosis in HCC patients. 5 , 8 This may be due to satellite nodules representing micrometastases formed through the portal vein system from the main tumor. Thus, even with clear margins after radical liver resection, patients with satellite nodules still face a higher risk of super-early recurrence.…”

“…In the current stage, the preoperative level of AFP has been proven to be useful for predicting early recurrence in HCC patients 2 , 4 , 5 , 8 , 17 , 24 However, the optimal cutoff value for AFP remains controversial. The widely used cutoff values in research are 20 ng/mL, 5 100 ng/mL, 24 and 400 ng/mL.…”

“…Zhang et al 4 found that tumor size, tumor number, macrovascular invasion, unsmooth tumor margin, peritumoral enhancement, and low peritumoral signal on HBP images were related to the early recurrence of HCC, especially macrovascular invasion and unsmooth tumor margin were considered to be independent predictors. Li et al 8 also found that invasion of large blood vessels was a key factor in predicting early recurrence of HCC. In addition, satellite nodules and single nodule with extraterritorial growth were also associated with recurrence.…”

“…We further found that patients with tumor size > 5cm, intratumoral hemorrhage, and confluent multinodular type were more prone to early recurrence. In addition, these studies also took into account lab indicators, such as preoperative AFP levels, 4 , 8 , 18 ALT or AST, 8 and ALP, 18 which also show great potential in predicting early postoperative HCC recurrence. Although these predictors are still being developed and refined, the presence of these factors may suggest that the tumor has a higher degree of malignancy and a worse prognosis.…”