Background and Aims: Current prediction models for early recurrence of hepatocellular carcinoma (HCC) after surgical resection remain unsatisfactory. The aim of this study was to develop evolutionary learning-derived prediction models with interpretability using both clinical and radiomic features to predict early recurrence of HCC after surgical resection. Methods: Consecutive 517 HCC patients receiving surgical resection with available contrast-enhanced computed tomography (CECT) images before resection were retrospectively enrolled. Patients were randomly assigned to a training set (n = 362) and a test set (n = 155) in a ratio of 7:3. Tumor segmentation of all CECT images including noncontrast phase, arterial phase, and portal venous phase was manually performed for radiomic feature extraction. A novel evolutionary learning-derived method called genetic algorithm for predicting recurrence after surgery of liver cancer (GARSL) was proposed to design prediction models for early recurrence of HCC within 2 years after surgery. Results: A total of 143 features, including 26 preoperative clinical features, 5 postoperative pathological features, and 112 radiomic features were used to develop GARSL preoperative and postoperative models. The area under the receiver operating characteristic curves (AUCs) for early recurrence of HCC within 2 years were 0.781 and 0.767, respectively, in the training set, and 0.739 and 0.741, respectively, in the test set. The accuracy of GARSL models derived from the evolutionary learning method was significantly better than models derived from other well-known machine learning methods or the early recurrence after surgery for liver tumor (ERASL) preoperative (AUC = 0.687, p #x3c; 0.001 vs. GARSL preoperative) and ERASL postoperative (AUC = 0.688, p #x3c; 0.001 vs. GARSL postoperative) models using clinical features only. Conclusion: The GARSL models using both clinical and radiomic features significantly improved the accuracy to predict early recurrence of HCC after surgical resection, which was significantly better than other well-known machine learning-derived models and currently available clinical models.
Liver Cancer

中文翻译：

---

用于预测肝细胞癌切除术后早期复发的进化学习衍生的临床放射模型

背景和目的：目前对手术切除后肝细胞癌 (HCC) 早期复发的预测模型仍不能令人满意。本研究的目的是开发具有可解释性的进化学习衍生预测模型，使用临床和影像学特征来预测手术切除后 HCC 的早期复发。方法：回顾性纳入连续 517 例接受手术切除且切除前可用对比增强计算机断层扫描 (CECT) 图像的 HCC 患者。患者被随机分配到一个训练集（ n = 362）和一个测试集（ n= 155)，比例为 7:3。手动执行所有 CECT 图像的肿瘤分割，包括非对比期、动脉期和门静脉期，以提取放射组学特征。提出了一种新的进化学习衍生方法，称为预测肝癌术后复发的遗传算法（GARSL），用于设计肝癌术后2年内早期复发的预测模型。结果：共有143个特征，包括26个术前临床特征、5个术后病理特征和112个影像组学特征，用于开发GARSL术前术后模型。2 年内 HCC 早期复发的受试者工作特征曲线下面积（AUC）在训练集中分别为 0.781 和 0.767，在测试集中分别为 0.739 和 0.741。源自进化学习方法的 GARSL 模型的准确性明显优于源自其他知名机器学习方法或肝肿瘤手术后早期复发 (ERASL) 术前的模型（AUC = 0.687，p #x3c；0.001 vs. GARSL 术前）和 ERASL 术后（AUC = 0.688，p#x3c; 0.001 与 GARSL 术后）模型仅使用临床特征。结论：结合临床和影像组学特征的 GARSL 模型显着提高了预测 HCC 手术切除后早期复发的准确性，明显优于其他知名的机器学习衍生模型和目前可用的临床模型。
肝癌