背景:尽管根治性手术切除是肝细胞癌(HCC)最有效的治疗方法,术后高复发率仍然是一个主要挑战,尤其是甲胎蛋白(AFP)阴性的HCC患者缺乏有效的术后复发监测生物标志物。新兴的影像组学可以通过分析术前对比增强计算机断层扫描(CECT)成像数据来揭示肿瘤的细微结构变化,并可能为预测AFP阴性HCC的早期复发(2年内复发)提供新的方法。在这项研究中,我们建议建立基于术前CECT的影像组学模型,以预测AFP阴性HCC术后早期复发的风险.
方法:本研究包括接受根治性切除术的AFP阴性HCC患者。使用计算机化工具从感兴趣的肿瘤区域(ROI)中提取影像组学特征,选择与患者术后复发相关的最佳影像学特征,并使用它们来构建放射学评分(RadScore),然后结合临床和随访信息,综合评价模型的可靠性。
结果:本研究共纳入148例AFP阴性HCC患者,从CECT中提取了1,977个影像学特征,其中2个是与AFP阴性HCC复发最相关的特征。他们在训练和验证队列中都有良好的预测能力,ROC曲线下面积(AUC)分别为0.709和0.764。肿瘤数量,微血管侵犯(MVI),AGPR和影像学特征是AFP阴性HCC患者术后早期复发的独立危险因素。训练和验证队列中整合模型的AUC分别为0.793和0.791。综合模型对AFP阴性HCC患者术后早期复发具有预测价值,这允许将患者分为早期复发的高风险和低风险亚组。
结论:结合临床和影像学特征构建的列线图在预测AFP阴性HCC患者术后早期复发的概率方面具有良好的表现。这有助于优化AFP阴性HCC患者的治疗决策和预后评估。
BACKGROUND: 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.
METHODS: 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.
RESULTS: 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.
CONCLUSIONS: 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.