Supplementary Material for: Evolutionary Learning-Derived Clinical-Radiomic Models for Predicting Early Recurrence of Hepatocellular Carcinoma after Resection

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 < 0.001 vs. GARSL preoperative) and ERASL postoperative (AUC = 0.688, p < 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.

背景与目的：当前肝细胞癌（hepatocellular carcinoma, HCC）术后早期复发的预测模型仍不尽如人意。本研究旨在结合临床与放射组学特征，开发具备可解释性的进化学习衍生预测模型，以预测肝细胞癌手术切除后的早期复发。
方法：连续纳入517例接受手术切除且术前拥有增强计算机断层扫描（contrast-enhanced computed tomography, CECT）影像资料的肝细胞癌患者，进行回顾性分析。按7:3的比例将患者随机分为训练集（n=362）与测试集（n=155）。对所有包含平扫期、动脉期及门静脉期的CECT影像进行手动肿瘤分割，以提取放射组学特征。本研究提出一种新型进化学习衍生方法——肝癌术后复发预测遗传算法（genetic algorithm for predicting recurrence after surgery of liver cancer, GARSL），用于构建术后2年内肝细胞癌早期复发的预测模型。
结果：共计纳入143项特征，包括26项术前临床特征、5项术后病理特征及112项放射组学特征，用于构建GARSL术前与术后模型。在训练集中，该模型对术后2年内肝细胞癌早期复发的受试者工作特征曲线下面积（area under the receiver operating characteristic curves, AUCs）分别为0.781与0.767；在测试集中则分别为0.739与0.741。相较于仅使用临床特征的其他经典机器学习模型，以及仅使用临床特征的肝癌术后早期复发（early recurrence after surgery for liver tumor, ERASL）术前模型（AUC=0.687，p<0.001，与GARSL术前模型相比）与ERASL术后模型（AUC=0.688，p<0.001，与GARSL术后模型相比），本研究基于进化学习方法构建的GARSL模型预测准确率显著更优。
结论：结合临床与放射组学特征的GARSL模型可显著提升肝细胞癌手术切除后早期复发的预测准确率，其性能显著优于其他经典机器学习衍生模型及现有临床模型。