Pfaehler Elisabeth, Mesotten Liesbet, Zhovannik Ivan, Pieplenbosch Simone, Thomeer Michiel, Vanhove Karolien, Adriaensens Peter, Boellaard Ronald
Department of Nuclear Medicine and Molecular Imaging, Medical Imaging Center, University of Groningen, University Medical Center Groningen, Groningen, The Netherlands.
Faculty of Medicine and Life Sciences, Hasselt University, Agoralaan building D, Diepenbeek, B-3590, Belgium.
Med Phys. 2021 Mar;48(3):1226-1238. doi: 10.1002/mp.14684. Epub 2021 Feb 6.
Radiomics refers to the extraction of a large number of image biomarker describing the tumor phenotype displayed in a medical image. Extracted from positron emission tomography (PET) images, radiomics showed diagnostic and prognostic value for several cancer types. However, a large number of radiomic features are nonreproducible or highly correlated with conventional PET metrics. Moreover, radiomic features used in the clinic should yield relevant information about tumor texture. In this study, we propose a framework to identify technical and clinical meaningful features and exemplify our results using a PET non-small cell lung cancer (NSCLC) dataset.
The proposed selection procedure consists of several steps. A priori, we only include features that were found to be reproducible in a multicenter setting. Next, we apply a voxel randomization step to identify features that reflect actual textural information, that is, that yield in 90% of the patient scans a value significantly different from random texture. Finally, the remaining features were correlated with standard PET metrics to further remove redundancy with common PET metrics. The selection procedure was performed for different volume ranges, that is, excluding lesions with smaller volumes in order to assess the effect of tumor size on the results. To exemplify our procedure, the selected features were used to predict 1-yr survival in a dataset of 150 NSCLC patients. A predictive model was built using volume as predictive factor for smaller, and one of the selected features as predictive factor for bigger lesions. The prediction accuracy of the both models were compared with the prediction accuracy of volume.
The number of selected features depended on the lesion size included in the analysis. When including the whole dataset, from 19 features reflecting actual texture only two were found to be not strongly correlated with conventional PET metrics. When excluding lesions smaller than 11.49 and 33.10 mL (25 and 50 percentile of the dataset), four out of 27 features and 13 out of 29 features remained after eliminating features highly correlated with standard PET metrics. When excluding lesions smaller than 103.9 mL (75 percentile), 33 out of 53 features remained. For larger lesions, some of these features outperformed volume in terms of classification accuracy (increase of 4-10%). The combination of using volume as predictor for smaller and one of the selected features for larger lesions also improved the accuracy when compared with volume only (increase from 72% to 76%).
When performing radiomic analysis for smaller lesions, it should be first carefully investigated if a textural feature reflects actual heterogeneity information. Next, verification of the absence of correlation with all conventional PET metrics is essential in order to assess the additional value of radiomic features. Radiomic analysis with lesions larger than 11.4 mL might give additional information to conventional metrics while at the same time reflecting actual tumor texture. Using a combination of volume and one of the selected features for prediction yields promise to increase accuracy and reliability of a radiomic model.
放射组学是指从医学图像中提取大量描述肿瘤表型的图像生物标志物。从正电子发射断层扫描（PET）图像中提取的放射组学特征对多种癌症类型具有诊断和预后价值。然而，大量的放射组学特征不可重复或与传统PET指标高度相关。此外，临床使用的放射组学特征应能提供有关肿瘤纹理的相关信息。在本研究中，我们提出了一个框架来识别具有技术和临床意义的特征，并使用PET非小细胞肺癌（NSCLC）数据集举例说明我们的结果。
所提出的选择程序包括几个步骤。先验地，我们只纳入在多中心环境中被发现可重复的特征。接下来，我们应用体素随机化步骤来识别反映实际纹理信息的特征，即在90%的患者扫描中产生与随机纹理有显著差异的值的特征。最后，将其余特征与标准PET指标进行相关性分析，以进一步去除与常见PET指标的冗余。针对不同的体积范围执行选择程序，即排除较小体积的病变，以评估肿瘤大小对结果的影响。为了举例说明我们的程序，在150例NSCLC患者的数据集中，使用所选特征预测1年生存率。构建了一个预测模型，对于较小的病变，使用体积作为预测因子；对于较大的病变，使用所选特征之一作为预测因子。将这两个模型的预测准确性与仅使用体积的预测准确性进行比较。
所选特征的数量取决于分析中包含的病变大小。当纳入整个数据集时，从19个反映实际纹理的特征中，仅发现两个与传统PET指标没有强相关性。当排除小于11.49和33.10 mL（数据集的第25和第50百分位数）的病变时，在消除与标准PET指标高度相关的特征后，27个特征中剩下4个，29个特征中剩下13个。当排除小于103.9 mL（第75百分位数）的病变时，53个特征中剩下33个。对于较大的病变，其中一些特征在分类准确性方面优于体积（提高了4 - 10%）。与仅使用体积相比，将体积作为较小病变的预测因子和将所选特征之一作为较大病变的预测因子相结合也提高了准确性（从72%提高到76%）。
在对较小病变进行放射组学分析时，应首先仔细研究纹理特征是否反映实际异质性信息。接下来，验证与所有传统PET指标均无相关性对于评估放射组学特征的附加价值至关重要。对大于11.4 mL的病变进行放射组学分析可能会为传统指标提供额外信息，同时反映实际肿瘤纹理。使用体积和所选特征之一的组合进行预测有望提高放射组学模型的准确性和可靠性。
