Center for Biomedical Image Computing and Analytics, Perelman School of Medicine, University of Pennsylvania, Philadephia, Pennsylvania.
Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadephia, Pennsylvania.
Neuro Oncol. 2018 Jul 5;20(8):1068-1079. doi: 10.1093/neuonc/noy033.
Epidermal growth factor receptor variant III (EGFRvIII) is a driver mutation and potential therapeutic target in glioblastoma. Non-invasive in vivo EGFRvIII determination, using clinically acquired multiparametric MRI sequences, could assist in assessing spatial heterogeneity related to EGFRvIII, currently not captured via single-specimen analyses. We hypothesize that integration of subtle, yet distinctive, quantitative imaging/radiomic patterns using machine learning may lead to non-invasively determining molecular characteristics, and particularly the EGFRvIII mutation.
We integrated diverse imaging features, including the tumor's spatial distribution pattern, via support vector machines, to construct an imaging signature of EGFRvIII. This signature was evaluated in independent discovery (n = 75) and replication (n = 54) cohorts of de novo glioblastoma, and compared with the EGFRvIII status obtained through an assay based on next-generation sequencing.
The cross-validated accuracy of the EGFRvIII signature in classifying the mutation status in individual patients of the independent discovery and replication cohorts was 85.3% (specificity = 86.3%, sensitivity = 83.3%, area under the curve [AUC] = 0.85) and 87% (specificity = 90%, sensitivity = 78.6%, AUC = 0.86), respectively. The signature was consistent with EGFRvIII+ tumors having increased neovascularization and cell density, as well as a distinctive spatial pattern involving relatively more frontal and parietal regions compared with EGFRvIII- tumors.
An imaging signature of EGFRvIII was found, revealing a complex, yet distinct macroscopic glioblastoma phenotype. By non-invasively capturing the tumor in its entirety, the proposed methodology can assist in evaluating the tumor's spatial heterogeneity, hence overcoming common spatial sampling limitations of tissue-based analyses. This signature can preoperatively stratify patients for EGFRvIII-targeted therapies, and potentially monitor dynamic mutational changes during treatment.
表皮生长因子受体变体 III（EGFRvIII）是胶质母细胞瘤的驱动突变和潜在治疗靶点。使用临床获得的多参数 MRI 序列进行非侵入性的体内 EGFRvIII 测定，可以帮助评估与 EGFRvIII 相关的空间异质性，目前通过单一标本分析无法捕捉到这种异质性。我们假设，通过机器学习整合细微但独特的定量成像/放射组学模式，可以实现非侵入性地确定分子特征，特别是 EGFRvIII 突变。
我们通过支持向量机整合了多种成像特征，包括肿瘤的空间分布模式，构建了 EGFRvIII 的成像特征。该特征在新诊断胶质母细胞瘤的独立发现（n=75）和复制（n=54）队列中进行了评估，并与基于下一代测序的检测获得的 EGFRvIII 状态进行了比较。
在独立发现和复制队列中，该 EGFRvIII 特征对个体患者突变状态的交叉验证准确率分别为 85.3%（特异性=86.3%，敏感性=83.3%，曲线下面积[AUC]=0.85）和 87%（特异性=90%，敏感性=78.6%，AUC=0.86）。该特征与 EGFRvIII+肿瘤具有更高的新生血管化和细胞密度一致，并且与 EGFRvIII-肿瘤相比，存在独特的空间模式，涉及更多的额区和顶区。
发现了一种 EGFRvIII 的成像特征，揭示了一种复杂但独特的宏观胶质母细胞瘤表型。通过非侵入性地捕获整个肿瘤，可以辅助评估肿瘤的空间异质性，从而克服组织分析中常见的空间采样局限性。该特征可在术前对 EGFRvIII 靶向治疗进行分层，并可能在治疗过程中监测动态突变变化。
