Moradmand Hajar, Molitoris Jason, Ling Xiao, Schumaker Lisa, Allor Erin, Thomas Hannah, Arons Danielle, Ferris Matthew, Krc Rebecca, Mendes William Silva, Tran Phuoc, Sawant Amit, Mehra Ranee, Gaykalova Daria A, Ren Lei
Department of Radiation Oncology, University of Maryland School of Medicine, Baltimore, MD, USA.
Department of Mathematics, Auburn University at Montgomery, Goodwyn Hall, Montgomery, USA.
Sci Rep. 2025 Jul 31;15(1):27995. doi: 10.1038/s41598-025-12161-w.
Radiomic biomarkers offer promise for precision oncology. However, their clinical utility is limited by variability from differing imaging protocols and the high dimensionality of radiomics data. Feature selection is key for better interpretability, accuracy, and efficiency, yet traditional methods lack stability and reproducibility. We investigate a Graph-Based Feature Selection (Graph-FS) approach that models feature interdependencies to identify stable radiomic signatures for head and neck squamous cell carcinoma (HNSCC) across institutions. We retrospectively analyzed 1,648 radiomic features extracted from the gross tumor volumes of 752 HNSCC patients from three institutions. After standard preprocessing and applying 36 radiomics parameter configurations to simulate variability, we compared Graph-FS with established methods: Boruta, Lasso, Recursive Feature Elimination (RFE), and Minimum Redundancy Maximum Relevance (mRMR). We evaluated feature selection stability and reproducibility using Pearson correlation, the Jaccard Index (JI), and the Dice-Sorensen Index (DSI) and assessed ranking consistency with Kendall's Coefficient of Concordance (W). Graph-FS achieved higher stability (JI = 0.46, DSI = 0.62, OP = 45.8%) versus baseline methods with JI of 0.005 (Boruta), 0.010 (Lasso), 0.006 (RFE) and 0.014 (mRMR). These results demonstrate that Graph-FS enhances feature stability, reproducibility, and predictive performance. This method could facilitate integration into AI-driven radiomics workflows for reliable, multi-center biomarker discovery.
放射组学生物标志物为精准肿瘤学带来了希望。然而，它们的临床应用受到不同成像协议的变异性和放射组学数据的高维度的限制。特征选择对于更好的可解释性、准确性和效率至关重要，但传统方法缺乏稳定性和可重复性。我们研究了一种基于图的特征选择（Graph-FS）方法，该方法对特征相互依赖性进行建模，以识别跨机构的头颈部鳞状细胞癌（HNSCC）的稳定放射组学特征。我们回顾性分析了从三个机构的752例HNSCC患者的大体肿瘤体积中提取的1648个放射组学特征。在进行标准预处理并应用36种放射组学参数配置来模拟变异性后，我们将Graph-FS与既定方法进行了比较：Boruta、套索回归、递归特征消除（RFE）和最小冗余最大相关性（mRMR）。我们使用皮尔逊相关性、杰卡德指数（JI）和迪赛-索伦森指数（DSI）评估了特征选择的稳定性和可重复性，并使用肯德尔和谐系数（W）评估了排名一致性。与基线方法相比，Graph-FS实现了更高的稳定性（JI = 0.46，DSI = 0.62，OP = 45.8%），而Boruta的JI为0.005，套索回归为0.010，RFE为0.006，mRMR为0.014。这些结果表明，Graph-FS增强了特征稳定性、可重复性和预测性能。该方法有助于集成到人工智能驱动的放射组学工作流程中，以进行可靠的多中心生物标志物发现。
