IEEE J Biomed Health Inform. 2019 Mar;23(2):795-804. doi: 10.1109/JBHI.2018.2825027. Epub 2018 Apr 9.
This paper presents a novel set of image texture features generalizing standard grey-level co-occurrence matrices (GLCM) to multimodal image data through joint intensity matrices (JIMs). These are used to predict the survival of glioblastoma multiforme (GBM) patients from multimodal MRI data. The scans of 73 GBM patients from the Cancer Imaging Archive are used in our study. Necrosis, active tumor, and edema/invasion subregions of GBM phenotypes are segmented using the coregistration of contrast-enhanced T1-weighted (CE-T1) images and its corresponding fluid-attenuated inversion recovery (FLAIR) images. Texture features are then computed from the JIM of these GBM subregions and a random forest model is employed to classify patients into short or long survival groups. Our survival analysis identified JIM features in necrotic (e.g., entropy and inverse-variance) and edema (e.g., entropy and contrast) subregions that are moderately correlated with survival time (i.e., Spearman rank correlation of 0.35). Moreover, nine features were found to be associated with GBM survival with a Hazard-ratio range of 0.38-2.1 and a significance level of p < 0.05 following Holm-Bonferroni correction. These features also led to the highest accuracy in a univariate analysis for predicting the survival group of patients, with AUC values in the range of 68-70%. Considering multiple features for this task, JIM features led to significantly higher AUC values than those based on standard GLCMs and gene expression. Furthermore, an AUC of 77.56% with p = 0.003 was achieved when combining JIM, GLCM, and gene expression features into a single radiogenomic signature. In summary, our study demonstrated the usefulness of modeling the joint intensity characteristics of CE-T1 and FLAIR images for predicting the prognosis of patients with GBM.
本文提出了一套新的图像纹理特征，通过联合强度矩阵 (JIM) 将标准灰度共生矩阵 (GLCM) 推广到多模态图像数据。这些特征用于从多模态 MRI 数据中预测胶质母细胞瘤 (GBM) 患者的生存情况。我们的研究使用了来自癌症成像档案 (Cancer Imaging Archive) 的 73 名 GBM 患者的扫描数据。通过对比增强 T1 加权 (CE-T1) 图像与其对应的液体衰减反转恢复 (FLAIR) 图像的配准，对 GBM 表型的坏死、活跃肿瘤和水肿/侵袭亚区进行分割。然后从这些 GBM 亚区的 JIM 中计算纹理特征，并使用随机森林模型将患者分为短生存期或长生存期组。我们的生存分析确定了坏死 (例如，熵和逆方差) 和水肿 (例如，熵和对比度) 亚区的 JIM 特征与生存时间中度相关 (即，Spearman 秩相关系数为 0.35)。此外，还发现了 9 个与 GBM 生存相关的特征，其风险比范围为 0.38-2.1，经 Holm-Bonferroni 校正后，其显著性水平为 p < 0.05。这些特征在预测患者生存组的单变量分析中也具有最高的准确性，AUC 值在 68-70%之间。考虑到这项任务中的多个特征，JIM 特征导致的 AUC 值明显高于基于标准 GLCM 和基因表达的 AUC 值。此外，当将 JIM、GLCM 和基因表达特征组合成一个单一的放射基因组特征时，AUC 达到了 77.56%，p = 0.003。总之，我们的研究表明，对 CE-T1 和 FLAIR 图像的联合强度特征进行建模对于预测 GBM 患者的预后是有用的。
