论著摘要 |【MR】临床适用同时又经生物学验证的MRI影像组学方法预测恶性胶质瘤基因组学蓝图和生存期(双语版)

2017-12-22 13:12:49 admin 1

Clinically Applicable and Biologically Validated MRI Radiomic Test Method Predicts Glioblastoma Genomic Landscape and Survival.

发表日期: 2016.08   来源:Neurosurgery. 2016 Aug;63 Suppl 1:156-7.

作者:

Zinn PO, Singh SK, Kotrotsou A, Zandi F, Thomas G, Hatami M, Luedi MM, Elakkad A, Hassan I, Gumin J, Sulman EP, Lang FF, Colen RR.

作者介绍:

1.

摘要

Abstact

简介

成像是对生物组织或者器官系统进行非侵入性的描述的一种方式;成像作为大多数疾病进程的早期诊断工具,正在迅速发展,进而也在改变我们诊断和跟踪患者的方式。大量的癌症成像特征已经与潜在的基因组学相关; 然而并没有一个确立了的因果关系。因此,我们的目标是测试成像与基因组信息之间是否存在因果关系; 同时开发临床相关的放射组学数据传输通道用于恶性胶质瘤分子表征的描述。

Introduction

Imaging is the modality of choice for noninvasive characterization of biological tissue and organ systems; imaging serves as early diagnostic tool for most disease processes and is rapidly evolving, thus transforming the way we diagnose and follow patients over time. A vast number of cancer imaging characteristics have been correlated to underlying genomics; however, none have established causality. Therefore, our objectives were to test if there is a causal relationship between imaging and genomicinformation; and to develop a clinically relevant radiomic pipeline for glioblastoma molecular characterization.

方法

使用基于RNA干扰的原位异种移植小鼠在体模型进行功能验证。自动化数据传输通道收集了4800个由MRI衍生的肿瘤纹理特征。使用单变量特征选择和增强树预测模型,得出患者特异性基因组概率图谱同时预测患者生存期(“癌症基因组图谱/ MD安德森数据集”)。

Methods

Functional validation was performed using a prototypic in vivo RNA-interference-based orthotopic xenograft mouse model. The automated pipeline collects 4800 MRI-derived texture features per tumor. Using univariate feature selection and boosted tree predictive modeling, a patient-specific genomic probability map was derived and patient survival predicted (The Cancer Genome Atlas/MD Anderson data sets).

结果

数据显示了显著的人类关联性异种移植(曲线下面积[AUC] 84%,P<0.001)。 此外,也从两个独立的数据集(AUC 90%,P <0.001)中,对表皮生长因子受体扩增(AUC 86%,P <0.0001),O-甲基鸟嘌呤-DNA-甲基转移酶甲基化/表达(AUC 92%,P = 0.001),恶性胶质瘤分子亚群(AUC 88%,P = 001),和生存期进行了预测。

Results

Data demonstrated a significant xenograft to human association (area under the curve [AUC] 84%, P < .001). Further, epidermal growth factor receptor amplification (AUC 86%, P < .0001), O-methylguanine-DNA-methyltransferase methylation/expression (AUC 92%, P = .001), glioblastoma molecular subgroups (AUC 88%, P = .001), and survival in 2 independent data sets (AUC 90%, P < .001) was predicted.

结论

我们的研究结果首次证明了成像特征与基因组肿瘤组成之间的因果关系。 我们提供一种可以直接临床适用的称为影像测序的成像分析方法,来允许自动图像分析,关键基因组事件的预测和存活。该方法是可扩展的,适用于任何类型的医学成像。此外,它允许进行人-鼠匹配的临床试验,深入的末端分析和基于影像组学的具有前瞻性的无创高分辨率的诊断,预后和预测性生物标志物开发。

Conclusions

Our results for the first time illustrate a causal relationship between imaging features and genomic tumor composition. We present a directly clinically applicable analytical imaging method termed Radiome Sequencing to allow for automated image analysis, prediction of key genomic events, and survival. This method is scalable and applicable to any type of medical imaging. Further, it allows for human-mouse matched coclinical trials, in-depth end point analysis, and upfront noninvasive high-resolution radiomics-based diagnostic, prognostic, and predictive biomarker development.

阅读原文:PMID: 27399418  DOI: 10.1227/01.neu.0000489709.98960.e1


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