Radiomics and clinical data predict pseudoprogression after radiotherapy in high-grade glioma

On conventional magnetic resonance imaging, pseudoprogression after radiotherapy for high-grade glioma may closely resemble true tumor progression, leading to unnecessary surgery, premature treatment escalation, or delayed appropriate therapy. We developed and internally validated an exploratory multivariable model for individualized pseudoprogression risk estimation.

This single-center retrospective cohort included 222 patients with World Health Organization 2021 central nervous system grade 3 or 4 glioma who underwent surgery followed by radiotherapy at Liuzhou Workers' Hospital from January 2015 to December 2024. Pseudoprogression was adjudicated before modeling through multidisciplinary review; 13 pseudoprogression cases had histopathological confirmation, and non-histologically confirmed cases required at least 6 months of stable or improved follow-up imaging. The complete two-reader radiomics matrix was analyzed using a strict split-first workflow. Dataset partitioning preceded ICC filtering, Z-score normalization, and LASSO modeling.

A total of 3,404 radiomic features were analyzed. After reproducibility filtering and LASSO selection, 17 radiomic features were retained to construct the locked RadScore. In the held-out validation cohort, the integrated model combining RadScore, rCBV, ADC, NLR, MGMT promoter methylation, and TMZ treatment achieved an AUC of 0.811 (95% CI: 0.696-0.925). The clinical-imaging model without RadScore achieved a validation AUC of 0.744 (95% CI: 0.614-0.873), whereas RadScore alone achieved an AUC of 0.771 (95% CI: 0.648-0.894).

The integrated model showed acceptable internal validation performance and provided a clinically interpretable framework for individualized PsP risk estimation by combining radiomic, perfusion-diffusion, inflammatory, molecular, and treatment-related information. External validation with standardized imaging protocols is warranted.