Robust Multicenter CT Radiogenomics for Dual EGFR and KRAS Prediction in Lung Cancer with Stability-Aware Modeling and SHAP Interpretation

TL;DR

This study evaluates radiomics and deep features from CT scans for predicting EGFR and KRAS mutations in lung cancer, emphasizing robustness, interpretability, and generalization across multiple centers.

Contribution

It benchmarks handcrafted and deep radiomic features, introduces a semi-supervised pseudo-labeling strategy, and demonstrates improved robustness and interpretability in multicenter mutation prediction.

Findings

HRF models achieved AUC 0.77 in external testing.

DFR models showed lower generalization with AUC around 0.57.

Fusion of HRF and DFR improved robustness but not always performance.

Abstract

Accurate identification of EGFR and KRAS mutations is essential for precision therapy in non-small cell lung cancer (NSCLC), but tissue genotyping is invasive and may not capture tumor heterogeneity. CT-based radiogenomics offers a noninvasive alternative, although generalization across centers remains challenging. We benchmarked handcrafted radiomics features (HRF), deep feature representations (DFR), and their fusion for three-class mutation prediction (wild-type, KRAS-mutant, and EGFR-mutant) with external testing. We curated 1,023 thoracic CT scans from 12 public datasets across more than 20 centers, including 136 patients with EGFR/KRAS labels. IBSI-compliant HRFs were extracted with standardized preprocessing, and DFRs were derived using PySERA. HRF-only, DFR-only, and fused HRF+DFR pipelines were evaluated using five-fold cross-validation and external testing. A semi-supervised pseudo-labeling strategy leveraged unlabeled CT scans, and SHAP supported interpretability. In external testing, HRF-based models generalized best, achieving AUC 0.77 +/- 0.07 and accuracy 0.77 +/- 0.00. DFR-based models showed a larger drop from cross-validation to external testing, with best external AUC around 0.57 +/- 0.05. Fusion improved robustness over DFR-only models but did not consistently outperform HRFs. SHAP identified morphology- and heterogeneity-related radiomic phenotypes as key predictors. Standardized handcrafted radiomics within a multicenter semi-supervised framework may provide a generalizable and interpretable approach for CT-based EGFR/KRAS stratification.