发表机构
Faculty of Mathematics and Informatics – Sofia University St. Kliment Ohridski（圣克莱门特奥赫里德斯基索非亚大学数学与信息学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究胶质母细胞瘤放射组学中特征稳健性与预测效用的关系，通过UPENN-GBM队列获取4752个特征，用ICC量化稳健性，经多种模型交叉验证，发现稳健性非特征选择可靠标准，放射组学特征纳入未超临床基线，稳健性过滤未提升性能。
AI 中文摘要
源自磁共振成像（MRI）的放射组学生物标志物已被广泛研究，作为胶质母细胞瘤（GBM）肿瘤特征描述和预后建模的非侵入性工具。然而，其临床转化仍然有限，部分原因是对肿瘤分割变异性敏感。在本研究中，我们使用宾夕法尼亚大学胶质母细胞瘤成像、基因组学和放射组学（UPENN-GBM）队列，系统地研究了GBM生存模型中特征稳健性与预测效用之间的关系。从三个肿瘤子区域（增强肿瘤（ET）、瘤周水肿（ED）和坏死核心（NC））的多参数MRI中获得了总共4752个放射组学特征。基于自动和专家优化的分割版本，使用组内相关系数（ICC）对特征稳健性进行量化。在具有有效ICC估计的特征中，48.1%被分类为稳健。使用Coxnet、随机生存森林和梯度提升生存分析模型进行交叉验证来评估生存预测。在这个队列中，放射组学特征的纳入并没有比临床基线有一致的改善，稳健性过滤也没有产生可检测的性能提升。模型选择的特征不如整体特征池稳健，这表明在稳健性方面缺乏富集。这些发现表明，仅稳健性并不是基于放射组学的生存建模中特征选择的可靠标准。
英文摘要
Radiomic biomarkers derived from magnetic resonance imaging (MRI) have been widely investigated as non-invasive tools for tumor characterization and prognostic modeling in glioblastoma (GBM). However, their clinical translation remains limited, in part due to sensitivity to tumor segmentation variability. In this study, we systematically investigate the relationship between feature robustness and predictive utility in GBM survival modeling using the University of Pennsylvania Glioblastoma Imaging, Genomics, and Radiomics (UPENN-GBM) cohort. A total of 4,752 radiomic features were obtained from multiparametric MRI across three tumor subregions: enhancing tumor (ET), peritumoral edema (ED), and necrotic core (NC). Feature robustness was quantified using the intraclass correlation coefficient (ICC) based on the automatic and expert-refined segmentation versions. Among features with valid ICC estimates, 48.1% were classified as robust. Survival prediction was evaluated using cross-validation with Coxnet, Random Survival Forest, and Gradient Boosting Survival Analysis models. In this cohort, radiomic feature inclusion showed no consistent improvement over the clinical baseline, and robustness filtering produced no detectable performance gain. Model-selected features were less robust than the overall feature pool, indicating a lack of enrichment for robustness. These findings suggest that robustness alone is not a reliable criterion for feature selection in radiomics-based survival modelling.
CommentsAccepted as a full paper at HCist 2026 and for publication in Procedia Computer Science
