Radiomics Repeatability Pitfalls in a Scan-Rescan MRI Study of Glioblastoma
Radiomics Repeatability Pitfalls in a Scan-Rescan MRI Study of Glioblastoma
复制标题
DOI：
10.1148/ryai.2020190199
复制
发表时间：
2021-01-01
期刊：
影响因子：
--
通讯作者：
Kalpathy-Cramer, Jayashree
中科院分区：
文献类型：
--
作者：
Hoebel, Katharina, V;Patel, Jay B.;Kalpathy-Cramer, Jayashree
目的：为了确定预处理对在扫描-再扫描胶质母细胞瘤MRI研究中使用流行的开源放射组学软件包提取的放射组学特征的可重复性和冗余度的影响。材料和方法：在这项研究中，对48例患者的T2加权液体衰减反转恢复（FLAIR）和T1加权增强后图像进行了二次分析，（平均年龄，56岁[范围，22-77岁]）被诊断患有胶质母细胞瘤的患者来自两项前瞻性研究（ClinicalTrials.gov NCT 00662506 [2009-2011]和NCT 00756106 [2008-2011]）。所有患者均在3-T MRI系统上使用相同的成像方案进行两次基线扫描，间隔2-6天。在扫描和再扫描之间没有进行治疗，肿瘤在视觉上基本上没有变化。通过使用PyRadiomics（https：//pyradiomics.readthedocs.io/）在不同条件下提取放射组学特征，包括归一化策略和强度量化。结果：形状特征的重复性高于强度特征（校正后P
Purpose: To determine the influence of preprocessing on the repeatability and redundancy of radiomics features extracted using a popular open-source radiomics software package in a scan-rescan glioblastoma MRI study.Materials and Methods: In this study, a secondary analysis of T2-weighted fluid-attenuated inversion recovery (FLAIR) and T1-weighted postcontrast images from 48 patients (mean age, 56 years [range, 22-77 years]) diagnosed with glioblastoma were included from two prospective studies (ClinicalTrials.gov NCT00662506 [2009-2011] and NCT00756106 [2008-2011]). All patients underwent two baseline scans 2-6 days apart using identical imaging protocols on 3-T MRI systems. No treatment occurred between scan and rescan, and tumors were essentially unchanged visually. Radiomic features were extracted by using PyRadiomics (https://pyradiomics.readthedocs.io/) under varying conditions, including normalization strategies and intensity quantization. Subsequently, intraclass correlation coefficients were determined between feature values of the scan and rescan.Results: Shape features showed a higher repeatability than intensity (adjusted P