论著摘要 |【CT】术前预测肝细胞癌早期发生的潜在生物标志物的基于CT的影像组学标记(双语版)

2017-08-30 11:19:58 admin 8

CT-based radiomics signature: a potential biomarker for preoperative prediction of earlyrecurrence in hepatocellular carcinoma.

发表日期:2017.6.9    来源:Abdom Radiol (NY). 

作者:Zhou Y1,2,3He L4Huang Y2Chen S1,2Wu P1,2Ye W2Liu Z5,6Liang C7,8.

作者介绍

    1.Graduate College, Southern Medical University, Guangzhou, 510515, China.

    2.Department of Radiology, Guangdong General Hospital, Guangdong Academy of Medical Sciences, 106 Zhongshan Er Road, Guangzhou, 510080, China.

    3.Department of Radiology, Mianyang Central Hospital, Mianyang, 621000, Sichuan Province, China.

    4.School of Medicine, South China University of Technology, Guangzhou, 510006, Guangdong, China.

    5.Graduate College, Southern Medical University, Guangzhou, 510515, China.

    6.Department of Radiology, Guangdong General Hospital, Guangdong Academy of Medical Sciences, 106 Zhongshan Er Road, Guangzhou, 510080, China.

    7.Graduate College, Southern Medical University, Guangzhou, 510515, China. 

    8.Department of Radiology, Guangdong General Hospital, Guangdong Academy of Medical Sciences, 106 Zhongshan Er Road, Guangzhou, 510080, China. 

目的

开发基于CT的放射性标记,并评估其术前预测肝细胞癌(HCC)早期复发(≤1年)的能力。

To develop a CT-based radiomics signature and assess its ability for preoperatively predicting the early recurrence (≤1 year) of hepatocellular carcinoma (HCC).

方法

本次回顾性研究共纳入215例接受部分肝切除术的HCC患者,所有患者至少接受1年内随访。从动脉和门静脉期CT图像中提取影像组学特征,通过最小绝对收缩和选择算子(LASSO)逻辑回归模型建立影像组学标记。评估与早期复发相关的术前临床因素。建立了影像组学标记,临床模型和组合模型,运用操作特征(ROC)曲线下面积(AUC)检测其区分早期复发的表现。



A total of 215 HCC patients who underwent partial hepatectomy were enrolled in this retrospective study, and all the patients were followed up at least within 1 year. Radiomics features were extracted from arterial- and portal venous-phase CT images, and a radiomics signature was built by the least absolute shrinkage and selection operator (LASSO) logistic regression model. Preoperative clinical factors associated with early recurrence were evaluated. A radiomics signature, a clinical model, and a combined model were built, and the area under the curve (AUC) of operating characteristics (ROC) was used to explore their performance to discriminate early recurrence.

结果

300个候选特征中选出21个影像组学特征,构建与早期复发显著相关的影像组学标记(P <0.001),并且他们在单独鉴别早期复发中表现出良好的表现,AUC0.81795CI 0.758-0.866),灵敏度为0.794,特异度为0.699。临床和联合模型的AUC分别为0.78195CI0.719-0.834)和0.83695CI0.779-0.883),灵敏度分别为0.7840.824,特异度分别为0.6190.708 。在常规临床变量中添加影像组学标记可以显著提高术前模型预测早期复发的准确性(P = 0.01)。

Twenty-one radiomics features were chosen from 300 candidate features to build a radiomics signature that was significantly associated with early recurrence (P < 0.001), and they presented good performance in the discrimination of early recurrence alone with an AUC of 0.817 (95% CI: 0.758-0.866), sensitivity of 0.794, and specificity of 0.699. The AUCs of the clinical and combined models were 0.781 (95% CI: 0.719-0.834) and 0.836 (95% CI: 0.779-0.883), respectively, with the sensitivity being 0.784 and 0.824, and the specificity being 0.619 and 0.708, respectively. Adding a radiomics signature into conventional clinical variables can significantly improve the accuracy of the preoperative model in predicting early recurrence (P = 0.01).

结论

影像组学标记是一种预测肝细胞癌早期复发的重要指标。将影像组学标记纳入常规临床因素与单独使用临床变量相比对术前早期复发的预测更好。

The radiomics signature was a significant predictor for early recurrence in HCC. Incorporating radiomics signature into conventional clinical factors performed better for preoperative estimation of early recurrence than with clinical variables alone.

关键词

计算机断层扫描,肝细胞癌,预测指标,影像组学标记,复发

Computed tomography; Hepatocellular carcinoma; Predictor; Radiomics signature; Recurrence


慧影医疗科技(北京)有限公司

地点:北京市海淀区中关村东升科技园B2-C103

电话:400-890-9020

邮箱:radcloud@huiyihuiying.com

关闭
图片
图片
  • 人工智能诊断云平台