Radiomic feature choices influence glioblastoma survival predictions
How Robust Are Prognostic Radiomic Features? Comparing Selection Techniques on Pooled Glioblastoma Cohorts
Computer Vision and Pattern RecognitionArtificial Intelligence
Summary
Glioblastoma is a serious brain cancer, and doctors often use MRI scans to find features that might predict how long patients will survive. This paper looked at hundreds of such features from MRI scans of many patients and tested three different methods to see which features seemed important. They found that different methods picked very different features, although a few key ones were consistently selected by all methods. This means that how researchers choose and analyze these MRI features can greatly affect the predictions made about patient survival.
What this means in practice
- •For medical imaging analysts: Select and evaluate MRI features for glioblastoma survival models with awareness of how analytic choices impact prognostic results.
- •For machine learning engineers: Develop more robust survival prediction models by comparing feature selection methods like log-rank tests, Cox regression, and SHAP with XGBoost on MRI data.
Authors
Yannick Sodonougbo, Marlene Schnieders, Alexia Rizoudis, Santiago Cepeda, Frank Kramer, Dominik Müller
Abstract
Radiomic survival studies in glioblastoma report heterogeneous prognostic features, but how much of this stems from the methodology itself is rarely examined. We analysed the association of 463 radiomic, anatomical and clinical features from pre-treatment MRI with overall survival in 705 IDH-wildtype glioblastoma patients from three public cohorts, using three techniques: a log-rank test after median split, univariate Cox regression (both Benjamini-Hochberg corrected) and an XGBoost regressor interpreted with SHAP. The log-rank test selected 99 features, Cox regression 72 and SHAP its top 20; five were selected by all three: age, a peritumoural T2 texture feature, the number of connected peritumoural mask components and two image-level intensity maxima. The two survival tests shared 51 features, about half of the SHAP top 20 were also selected by either test, and where selections overlapped, effect directions agreed. Many selections were PyRadiomics diagnostic descriptors that are not restricted to tumour voxels. Analytical pipeline choices, including ranking method, pre-filtering and descriptor handling, can substantially influence which features appear prognostic.