From the Jiangsu Key Laboratory of Molecular and Functional Imaging, Department of Radiology, Zhongda Hospital, School of Medicine, Southeast University, 87 Ding Jia Qiao Road, Nanjing, China 210009 (T.Y.X., X.P.M., J.H.Z., Q.Y., W.L.W., Y.C.W., T.Y.T., S.H.J.); Institute for AI in Medicine, School of Artificial Intelligence, Nanjing University of Information Science and Technology, Nanjing, China (Z.H.Z., J.X.); MR Scientific Marketing, Siemens Healthineers, Shanghai, China (Y.S.); Department of Radiology, The Third Affiliated Hospital of Nantong University, Nantong, China (T.Z.); Department of Radiology, The Xiangya Hospital of Central South University, Changsha, China (X.Y.L.); Department of Radiology, Department of Hepatobiliary Surgery, The First Affiliated Hospital of Kunming Medical University, Kunming, China (Y.L.); and Department of Radiology, The First Affiliated Hospital of Zhejiang University School of Medicine, Hangzhou, China (W.B.X.).
Radiology. 2023 May;307(4):e222729. doi: 10.1148/radiol.222729. Epub 2023 Apr 25.
Background Prediction of microvascular invasion (MVI) may help determine treatment strategies for hepatocellular carcinoma (HCC). Purpose To develop a radiomics approach for predicting MVI status based on preoperative multiphase CT images and to identify MVI-associated differentially expressed genes. Materials and Methods Patients with pathologically proven HCC from May 2012 to September 2020 were retrospectively included from four medical centers. Radiomics features were extracted from tumors and peritumor regions on preoperative registration or subtraction CT images. In the training set, these features were used to build five radiomics models via logistic regression after feature reduction. The models were tested using internal and external test sets against a pathologic reference standard to calculate area under the receiver operating characteristic curve (AUC). The optimal AUC radiomics model and clinical-radiologic characteristics were combined to build the hybrid model. The log-rank test was used in the outcome cohort (Kunming center) to analyze early recurrence-free survival and overall survival based on high versus low model-derived score. RNA sequencing data from The Cancer Image Archive were used for gene expression analysis. Results A total of 773 patients (median age, 59 years; IQR, 49-64 years; 633 men) were divided into the training set ( = 334), internal test set ( = 142), external test set ( = 141), outcome cohort ( = 121), and RNA sequencing analysis set ( = 35). The AUCs from the radiomics and hybrid models, respectively, were 0.76 and 0.86 for the internal test set and 0.72 and 0.84 for the external test set. Early recurrence-free survival ( < .01) and overall survival ( < .007) can be categorized using the hybrid model. Differentially expressed genes in patients with findings positive for MVI were involved in glucose metabolism. Conclusion The hybrid model showed the best performance in prediction of MVI. © RSNA, 2023 See also the editorial by Summers in this issue.
背景 微血管侵犯（MVI）的预测有助于确定肝细胞癌（HCC）的治疗策略。目的 基于术前多期 CT 图像开发一种用于预测 MVI 状态的放射组学方法，并确定与 MVI 相关的差异表达基因。材料与方法 本研究回顾性纳入了 2012 年 5 月至 2020 年 9 月来自 4 家医疗中心的经病理证实的 HCC 患者。在术前登记或减影 CT 图像上，从肿瘤和肿瘤周围区域提取放射组学特征。在训练集中，通过特征降维，使用逻辑回归为每个特征构建 5 个放射组学模型。使用内部和外部测试集对病理参考标准进行测试，计算受试者工作特征曲线下面积（AUC）。将最佳 AUC 放射组学模型与临床-放射学特征相结合，构建混合模型。对数秩检验用于昆明中心的结果队列，根据高、低模型衍生评分分析早期无复发生存率和总生存率。使用癌症影像档案中的 RNA 测序数据进行基因表达分析。结果 共纳入 773 例患者（中位年龄，59 岁；四分位数范围，49~64 岁；633 例男性），分为训练集（n=334）、内部测试集（n=142）、外部测试集（n=141）、结果队列（n=121）和 RNA 测序分析集（n=35）。内部测试集和外部测试集的放射组学模型和混合模型的 AUC 分别为 0.76 和 0.86，0.72 和 0.84。使用混合模型可以对早期无复发生存率（<.01）和总生存率（<.007）进行分类。MVI 阳性患者的差异表达基因参与葡萄糖代谢。结论 混合模型在预测 MVI 方面表现最佳。RSNA，2023 本期还见 Summers 的社论。
