Radiomics feature stability of open-source software evaluated on apparent diffusion coefficient maps in head and neck cancer.
Radiomics feature stability of open-source software evaluated on apparent diffusion coefficient maps in head and neck cancer.
复制标题
DOI：
10.1038/s41598-021-96600-4
复制
发表时间：
2021-09-03
影响因子：
4.6
通讯作者：
Ng SP
中科院分区：
文献类型：
--
作者：
Korte JC;Cardenas C;Hardcastle N;Kron T;Wang J;Bahig H;Elgohari B;Ger R;Court L;Fuller CD;Ng SP
放射组学是一种很有前途的技术，用于发现基于图像的癌症治疗反应生物标志物。放射组学特征的可重复性是图像生物标志物标准化倡议（IBSI）解决的一个已知问题，但解释先前发表的放射组学特征仍然具有挑战性。本研究调查了两种广泛使用的放射组学软件包（IBEX, MaZda）与IBSI兼容软件包（PyRadiomics）相比计算放射组学特征的可重复性。对来自PREDICT-HN观察放疗研究的59例头颈癌（HNC）患者的334张扩散加权磁共振图像进行强度直方图、形状和纹理特征提取。基于名称和线性相关性，PyRadiomics与IBEX共有83个特征，与马自达共有49个特征，相关良好的特征子集被认为是可重复的（IBEX: 15个特征，马自达：18个特征）。我们探讨了在HNC放射治疗反应模型中包括不可重复放射组学特征的影响。使用来自任一软件的放射学特征对等效患者组进行分类是可能的，但只有当使用相关阈值方法将模型限制为可靠特征时才有可能。这与临床生物标志物验证试验相关，因为它提供了一个框架来评估现有试验中报告的放射学特征的可重复性。
Radiomics is a promising technique for discovering image based biomarkers of therapy response in cancer. Reproducibility of radiomics features is a known issue that is addressed by the image biomarker standardisation initiative (IBSI), but it remains challenging to interpret previously published radiomics signatures. This study investigates the reproducibility of radiomics features calculated with two widely used radiomics software packages (IBEX, MaZda) in comparison to an IBSI compliant software package (PyRadiomics). Intensity histogram, shape and textural features were extracted from 334 diffusion weighted magnetic resonance images of 59 head and neck cancer (HNC) patients from the PREDICT-HN observational radiotherapy study. Based on name and linear correlation, PyRadiomics shares 83 features with IBEX and 49 features with MaZda, a sub-set of well correlated features are considered reproducible (IBEX: 15 features, MaZda: 18 features). We explore the impact of including non-reproducible radiomics features in a HNC radiotherapy response model. It is possible to classify equivalent patient groups using radiomic features from either software, but only when restricting the model to reliable features using a correlation threshold method. This is relevant for clinical biomarker validation trials as it provides a framework to assess the reproducibility of reported radiomic signatures from existing trials.
登录
查看更多内容
影响因子：
2.5
作者：
Collewet, G;Strzelecki, M;Mariette, F
通讯作者：
Mariette, F
影响因子：
3.6
作者：
Jeon, Seung Hyuck;Song, Changhoon;Kim, Jae-Sung
通讯作者：
Kim, Jae-Sung
影响因子：
2.5
作者：
Jansen, Jacobus F. A.;Lu, Yonggang;Shukla-Dave, Amita
通讯作者：
Shukla-Dave, Amita
影响因子：
4.4
作者：
Crombe, Amandine;Perier, Cynthia;Saut, Olivier
通讯作者：
Saut, Olivier
影响因子：
3.8
作者：
Apte, Aditya P.;Iyer, Aditi;Deasy, Joseph O.
通讯作者：
Deasy, Joseph O.