论著摘要 |【CT】静态和呼吸门控CT扫描的放射组学数据与立体定向放疗法肺癌患者疾病复发相关性研究(双语版)

2017-08-21 16:53:27 admin 131

Associations of Radiomic Data Extracted from Static and Respiratory-Gated CT Scans with Disease Recurrence in Lung Cancer Patients Treated with SBRT.

发表日期:2017.6.3    来源:PLoS One. 

作者:Huynh E1Coroller TP1Narayan V1Agrawal V1Romano J1Franco I1Parmar C1Hou Y1Mak RH1Aerts HJ1,2.

作者介绍

  1. Department of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women's Hospital, Harvard Medical School, Boston, United States of America.

  2. Department of Radiology, Dana-Farber Cancer Institute, Brigham and Women's Hospital, Harvard Medical School, Boston, United States of America.

摘要

放射组学的目的是定量的捕获医学影像中复杂的肿瘤特征,并把它们与临床结果相关联。这项研究旨在探究不同的CT成像对于预测早期非小细胞肺癌(NSCLC)患者的放射组学特征的影响,这些患者所采用的是立体定向放疗疗法(SBRT)。我们分析了112位用SBRT治疗的NSCLC患者的影像,其中包括静态自由呼吸(FB)和平均密度投影(AIP)。基于稳定性和可变性,对于每一个影像(FB或者AIP)都用19种放射学的特征进行分析,而其中有6种是两种影像特征共有的,另外的13在种是特异的。使用一致性指数(CI)评估远处转移(DM)和局部复发(LRR)特征的预后表现,并与两个常规特征(肿瘤体积和最大直径)进行比较。 使用假发现率程序对P值进行多次测试。 没有FB辐射特征与DM相关,然而,描述肿瘤形状和异质性的七个AIP辐射特征是(CI范围:0.638-0.676)。 FB图像的传统特征与DM无关,但AIP常规特征为(CI范围:0.643-0.658)。 使用交叉验证在FB和AIP图像之间比较了放射组学和常规多变量模型。 使用置换检验来评估模型之间的差异。AIP放射组学多变量模型(中值CI = 0.667)在预测DM中优于其他所有模型(中值CI范围:0.601-0.630)。 没有一个成像特征能预测LRR。 因此,影像类型影响放射组学模型与疾病复发相关的表现。 AIP图像包含比FB图像更多的信息,这些图像与用SBRT治疗的早期NSCLC患者的疾病复发相关,这表明AIP图像可能对于成像生物标志物的开发更有优势。

Radiomics aims to quantitatively capture the complex tumor phenotype contained in medical images to associate them with clinical outcomes. This study investigates the impact of different types of computed tomography (CT) images on the prognostic performance of radiomic features for disease recurrence in early stage non-small cell lung cancer (NSCLC) patients treated with stereotactic body radiation therapy (SBRT). 112 early stage NSCLC patients treated with SBRT that had static free breathing (FB) and average intensity projection (AIP) images were analyzed. Nineteen radiomic features were selected from each image type (FB or AIP) for analysis based on stability and variance. The selected FB and AIP radiomic feature sets had 6 common radiomic features between both image types and 13 unique features. The prognostic performances of the features for distant metastasis (DM) and locoregional recurrence (LRR) were evaluated using the concordance index (CI) and compared with two conventional features (tumor volume and maximum diameter). P-values were corrected for multiple testing using the false discovery rate procedure. None of the FB radiomic features were associated with DM, however, seven AIP radiomic features, that described tumor shape and heterogeneity, were (CI range: 0.638-0.676). Conventional features from FB images were not associated with DM, however, AIP conventional features were (CI range: 0.643-0.658). Radiomic and conventional multivariate models were compared between FB and AIP images using cross validation. The differences between the models were assessed using a permutation test. AIP radiomic multivariate models (median CI = 0.667) outperformed all other models (median CI range: 0.601-0.630) in predicting DM. None of the imaging features were prognostic of LRR. Therefore, image type impacts the performance of radiomic models in their association with disease recurrence. AIP images contained more information than FB images that were associated with disease recurrence in early stage NSCLC patients treated with SBRT, which suggests that AIP images may potentially be more optimal for the development of an imaging biomarker.


阅读原文:10.1371/journal.pone.0169172




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