治疗后胶质瘤的体素明智放射学栖息地分析，用于无创区分真进展和假进展
Voxel-Wise Radiomics Habitat Analysis of Posttreatment Gliomas for Noninvasive Differentiation of True Progression and Pseudoprogression.
摘要(中文译文)
胶质瘤放化疗后，鉴别真性进展（TP）与假性进展（PsP）仍具挑战性，因为常规MRI表现存在重叠。评估体素级影像组学栖息地指标能否改善TP/PsP分类并补充临床和分子特征。回顾性、多中心研究。193例治疗后胶质瘤患者：训练集121例（54.2±11.3岁；男74例；85例TP/36例PsP），外部测试集72例（51.4±10.4岁；男44例；52例TP/20例PsP）。3 T和1.5 T；对比增强T1加权自旋回波成像（T1CE）、T2加权快速/涡轮自旋回波成像（T2WI）、T2加权液体衰减反转恢复快速/涡轮自旋回波成像（T2-FLAIR）、弥散加权平面回波成像（DWI）和动脉自旋标记（ASL）。从对比增强肿瘤ROI中提取体素级影像组学特征。高斯混合模型生成软栖息地，并据此计算体素级指标。构建了三个模型。临床模型包括肿瘤分级、异柠檬酸脱氢酶（IDH）状态、O6-甲基鸟嘌呤-DNA甲基转移酶（MGMT）启动子甲基化状态和时间间隔。特征选择采用最小绝对收缩和选择算子（LASSO）；分类器优化采用基于Optuna的贝叶斯方法。采用受试者工作特征（ROC）曲线分析、校准曲线、决策曲线分析（DCA）和SHAP。p<0.05表示差异有统计学意义。在测试集中，临床模型、体素级栖息地模型和联合模型的曲线下面积（AUC）分别为0.701（95%置信区间[CI]：0.597-0.806）、0.832（95%CI：0.736-0.917）和0.890（95%CI：0.819-0.958）。联合模型显著优于临床模型（差值0.189）。体素级栖息地模型与临床模型比较（差值0.131；p=0.164）以及联合模型与体素级栖息地模型比较（差值0.058；p=0.105）均无统计学意义。SHAP将CBF_habitat_edge_standard_deviation、CBF_habitat_entropy_mean和T1CE_habitat_edge_standard_deviation列为主要贡献因素。体素级栖息地分析结合临床和分子特征，通过可解释的异质性指标改善了TP/PsP鉴别。3期。
Abstract
Differentiating true progression (TP) from pseudoprogression (PsP) after chemoradiotherapy in gliomas remains challenging because conventional MRI findings overlap. To assess whether voxel-level radiomics habitat metrics improve TP/PsP classification and complement clinical and molecular features. Retrospective, multi-center. 193 glioma patients after treatment: 121 in the training set (54.2 ± 11.3 years; 74 men; 85 TP/36 PsP) and 72 in the external testing set (51.4 ± 10.4 years; 44 men; 52 TP/20 PsP). 3 and 1.5 T; contrast-enhanced T1-weighted spin-echo imaging (T1CE), T2-weighted fast/turbo spin-echo imaging (T2WI), T2-weighted fluid-attenuated inversion recovery fast/turbo spin-echo imaging (T2-FLAIR), diffusion-weighted echo-planar imaging (DWI), and arterial spin labeling (ASL). Voxel-wise radiomics features were extracted from contrast-enhancing tumor ROIs. Gaussian mixture models generated soft habitats, from which voxel-level metrics were calculated. Three models were constructed. The Clinical Model included tumor grade, isocitrate dehydrogenase (IDH) status, O6-methylguanine-DNA methyltransferase (MGMT) promoter methylation status, and time interval. Feature selection used least absolute shrinkage and selection operator (LASSO); classifier optimization employed Optuna-based Bayesian methods. Receiver operating characteristic (ROC) curve analysis, calibration curves, decision curve analysis (DCA), and SHAP were used. p < 0.05 indicated significance. In the testing set, the Clinical, Voxel-wise Habitat, and Combined Models achieved areas under the curve (AUCs) of 0.701 (95% confidence interval [CI]: 0.597-0.806), 0.832 (95% CI: 0.736-0.917), and 0.890 (95% CI: 0.819-0.958), respectively. The Combined Model significantly outperformed the clinical model (difference, 0.189). Voxel-wise Habitat versus Clinical (difference, 0.131; p = 0.164) and Combined versus Voxel-wise Habitat comparisons (difference, 0.058; p = 0.105) were not significant. SHAP ranked CBF_habitat_edge_standard_deviation, CBF_habitat_entropy_mean, and T1CE_habitat_edge_standard_deviation as leading contributors. Voxel-wise habitat analysis, combined with clinical and molecular features, improved TP/PsP discrimination with interpretable heterogeneity metrics. 3. Stage 3.
如何引用
AMA
Linsha Yang, Defeng Liu, Duo Zhang, Juan Du, Qinglei Shi, Tao Zheng. Voxel-Wise Radiomics Habitat Analysis of Posttreatment Gliomas for Noninvasive Differentiation of True Progression and Pseudoprogression.. Journal of magnetic resonance imaging : JMRI. 2026; doi:10.1002/jmri.70419.
APA
Linsha Yang, Defeng Liu, Duo Zhang, Juan Du, Qinglei Shi, Tao Zheng (2026). Voxel-Wise Radiomics Habitat Analysis of Posttreatment Gliomas for Noninvasive Differentiation of True Progression and Pseudoprogression.. Journal of magnetic resonance imaging : JMRI. https://doi.org/10.1002/jmri.70419
GB/T 7714
Linsha Yang, Defeng Liu, Duo Zhang, Juan Du, Qinglei Shi, Tao Zheng. Voxel-Wise Radiomics Habitat Analysis of Posttreatment Gliomas for Noninvasive Differentiation of True Progression and Pseudoprogression.[J]. Journal of magnetic resonance imaging : JMRI, 2026 doi:10.1002/jmri.70419.
在 PubMed增强版 阅读全文
翻译全文 · AI 文献问答 · PDF 原文下载 · 引用导出