论著摘要 |【CT】用不同疾病特异存活率比较放射性生物标志物和体积分析来解码肺腺癌肿瘤表型(双语版)

2017-08-13 15:00:41 admin 57

Comparison of a radiomic biomarker with volumetric analysis for decoding tumour phenotypes of lung adenocarcinoma with different disease-specific survival.

发表日期:2017.3.18    来源:Eur Radiol

作者:Yuan M1Zhang YD1Pu XH1Zhong Y1Li H2Wu JF3Yu TF4.

作者介绍

  1. Department of Radiology, the First Affiliated Hospital of Nanjing Medical University, 300, Guangzhou Road, Nanjing, Jiangsu Province, China, 210009.

  2. Department of Pathology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, China, 210009.

  3. GE Healthcare, Shanghai, China, 210000.

  4. Department of Radiology, the First Affiliated Hospital of Nanjing Medical University, 300, Guangzhou Road, Nanjing, Jiangsu Province, China, 210009. 

目的

比较基于多特征的放射性生物标志物与体积分析在计算机断层扫描(CT)扫描中区分不同疾病特异性存活肺腺癌。

To compare a multi-feature-based radiomic biomarker with volumetric analysis in discriminating lung adenocarcinomas with different disease-specific survival on computed tomography (CT) scans.

方法

该回顾性研究获得机构审查委员会的批准,并且符合“健康保险可移植性和责任法案”(HIPAA)。 CT鉴定出有半固体结节的肺腺癌(n=431)。 使用计算机辅助分割方法测量体积和固体百分比。从分段感兴趣体积(VOI)中提取量化强度,纹理和微波的辐射特征。通过使用Relief方法选择了二十个最佳特征,并随后进入支持向量机(SVM),用于区分原位腺癌(AIS/微创腺癌(MIA)和浸润性腺癌(IAC)。将放射性标记的表现与通过受试者操作曲线(ROC)分析和逻辑回归分析的体积分析进行比较。



This retrospective study obtained institutional review board approval and was Health Insurance Portability and Accountability Act (HIPAA) compliant. Pathologically confirmed lung adenocarcinoma (n = 431) manifested as subsolid nodules on CT were identified. Volume and percentage solid volume were measured by using a computer-assisted segmentation method. Radiomic features quantifying intensity, texture and wavelet were extracted from the segmented volume of interest (VOI). Twenty best features were chosen by using the Relief method and subsequently fed to a support vector machine (SVM) for discriminating adenocarcinoma in situ (AIS)/minimally invasive adenocarcinoma (MIA) from invasive adenocarcinoma (IAC). Performance of the radiomic signatures was compared with volumetric analysisvia receiver-operating curve (ROC) analysis and logistic regression analysis.

结果

ROC分析(Az值为0.829;灵敏度为72.1%,特异度为80.9%)区分原位腺癌(AIS/微创腺癌(MIA)和浸润性腺癌(IAC)的放射特征的准确性达到80.5%,其准确性明显高于体积分析(69.5%P=0.049)回归分析显示,放射性标记对体积分析具有优越的预后性能,AIC值分别为81.2%,70.8%。回归分析显示,放射性标记比体积分析具有优越的预后性能,AIC值分别为81.2%,70.8%。



The accuracy of proposed radiomic signatures for predicting AIS/MIA from IAC achieved 80.5% with ROC analysis (Az value, 0.829; sensitivity, 72.1%; specificity, 80.9%), which showed significantly higher accuracy than volumetric analysis (69.5%, P = 0.049). Regression analysis showed that radiomic signatures had superior prognostic performance to volumetric analysis, with AIC values of 81.2% versus 70.8%, respectively.

结论

在区分不同疾病特异性生存的肺腺癌方面,放射性肿瘤 - 表型生物标志物比传统体积分析显示出更好的诊断准确性。



The radiomic tumour-phenotypes biomarker exhibited better diagnostic accuracy than traditional volumetric analysis in discriminating lung adenocarcinoma with different disease-specific survival.

关键点

设计CT上的放射性生物标志物来鉴定肺腺癌的表型•对表现有半固体结节的肺腺癌放射性标志物•回顾性研究显示放射性标记的诊断准确度高于体积分析•放射学有助于评估肺腺癌内肿瘤异质性•可以更有信心地给予医学决策。

Radiomic biomarker on CT was designed to identify phenotypes of lung adenocarcinoma • Built up radiomic signature for lung adenocarcinoma manifested as subsolid nodules • Retrospective study showed radiomic signature had greater diagnostic accuracy than volumetric analysis • Radiomics help to evaluate intratumour heterogeneity within lung adenocarcinoma • Medical decision can be given with more confidence.

关键词

肺腺癌,生物标志物,CT检查,放射学,容积

Adenocarcinoma of lung; Biomarker; Computed tomography; Radiomics; Volumetric


阅读原文:10.1007/s00330-017-4855-3



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