用于预测胶质母细胞瘤治疗反应的多参数MRI放射组学与机器学习框架
Multiparametric MRI Radiomics and Machine Learning Framework for Predicting Treatment Response in Glioblastoma
AI总结：
本研究构建结合多参数MRI放射组学与MGMT状态的随机森林模型，实现胶质母细胞瘤放化疗后真性进展与假性进展的无创精准区分，性能优于多种对照方法。
AI中文摘要：
在胶质母细胞瘤（GBM）患者放化疗后，区分真性进展（TP）与假性进展（PsP）仍是重大诊断挑战，二者在常规增强后MRI上表现极为相似。这种区分具有重要临床意义，因为TP与PsP的处理方案截然不同，但仅靠常规影像学无法可靠区分。本研究探讨从动态对比增强（DCE）MRI的简约体素水平药代动力学模型中提取的放射组学特征，联合MGMT状态是否能区分二者。研究队列包含82例IDH野生型GBM成人患者，均在放化疗后6个月内出现新的增强病灶；分类依据为：可行组织病理学检查者（n=52）采用病理结果，其余（n=30）采用改良RANO标准。对每个体素，将对比剂浓度时间曲线拟合至5种候选药代动力学模型，通过AIC最小化保留最优拟合，生成简约的Ktrans、Ve、Vp和taui图，适配肿瘤局部异质性，而非对整个肿瘤采用单一固定模型。分割后，提取1073个放射组学描述符，经Mann-Whitney U检验筛选和弹性网（Elastic Net）降维，随后用于4种特征配置下训练5种分类器。结合简约DCE-MRI放射组学与MGMT状态的随机森林分类器实现了最佳区分性能：平均AUC为0.89，灵敏度0.93，特异性0.76，F1值0.90，优于不含MGMT的特征（AUC 0.84）、T1增强基线（AUC 0.72）及单模型扩展Tofts分析（AUC 0.68）。Ktrans图的形状与纹理描述符联合肿瘤体积是最强预测因子，MGMT则贡献较小的独立效应。允许模型随体素变化可提升无创区分效果。
英文摘要：
Distinguishing True Progression (TP) from Pseudo-Progression (PsP) after chemoradiotherapy remains a major diagnostic challenge in GBM, as both entities present near-identical appearances on conventional contrast-enhanced post-treatment MRI. This distinction carries substantial clinical weight, since TP and PsP demand divergent management yet cannot be reliably separated on routine imaging alone. We investigated whether radiomic features derived from a parsimonious, voxel-wise pharmacokinetic model of dynamic contrast-enhanced (DCE) MRI, combined with MGMT status, could discriminate between the two. The cohort comprised 82 adults with IDH-wildtype GBM who developed a new contrast-enhancing lesion within six months of chemoradiotherapy; classification (53 TP, 29 PsP) was established by histopathology where available (n=52) and modified RANO criteria otherwise (n=30). At every voxel, contrast-concentration time courses were fitted to five candidate pharmacokinetic models, and the best fit was retained by AIC minimisation, yielding parsimonious Ktrans, Ve, Vp, and taui maps adapting to local heterogeneity rather than a single fixed model across the tumour. Following segmentation, 1,073 radiomic descriptors were extracted and reduced via Mann-Whitney U filtering and Elastic Net, then used to train five classifiers across four feature configurations. A Random Forest classifier combining parsimonious DCE-MRI radiomics with MGMT status achieved the best discrimination (mean AUC 0.89, sensitivity 0.93, specificity 0.76, F1 0.90), outperforming features without MGMT (0.84), a T1-post-contrast baseline (0.72), and a single-model extended-Tofts analysis (0.68). Shape and textural descriptors of the Ktrans map, with tumour volume, were the strongest predictors, MGMT contributing a smaller, independent effect. Allowing the model to vary voxel-wise improves non-invasive discrimination.
