Replication study of PD-L1 status prediction in NSCLC using PET/CT radiomics

• Published in: European journal of radiology 2025-02, Vol.183, p.111825, Article 111825
• Main Authors: Stüber, Anna Theresa, Heimer, Maurice M., Ta, Johanna, Fabritius, Matthias P., Hoppe, Boj F., Sheikh, Gabriel, Brendel, Matthias, Unterrainer, Lena, Jurmeister, Philip, Tufman, Amanda, Ricke, Jens, Cyran, Clemens C., Ingrisch, Michael
• Format: Article
• Language: English
• Subjects: Machine learning benchmark; NSCLC; PD-L1; PET/CT imaging data; Radiomics; Replication study
• ISSN: 0720-048X; 1872-7727; 1872-7727
• DOI: 10.1016/j.ejrad.2024.111825

This study investigates the predictive capability of radiomics in determining programmed cell death ligand 1 (PD-L1) expression (>=1%) status in non-small cell lung cancer (NSCLC) patients using a newly collected [18F]FDG PET/CT dataset. We aimed to replicate and validate the radiomics-based machine learning (ML) model proposed by Zhao et al. [1] predicting PD-L1 status from PET/CT-imaging. An independent cohort of 254 NSCLC patients underwent [18F]FDG PET/CT imaging, with primary tumor segmentation conducted using lung tissue window (LTW) and more conservative soft tissue window (STW) methods. Radiomics models (“Rad-score” and “complex model”) and a clinical-stage model from Zhao et al. were evaluated via 10-fold cross-validation and AUC analysis, alongside a benchmark-study comparing different ML-model pipelines. Clinicopathological data were collected from medical records. On our data, the Rad-score model yielded mean AUCs of 0.593 (STW) and 0.573 (LTW), below Zhao et al.’s 0.761. The complex model achieved mean AUCs of 0.505 (STW) and 0.519 (LTW), lower than Zhao et al.’s 0.769. The clinical model showed a mean AUC of 0.555, below Zhao et al.’s 0.64. All models performed significantly lower than Zhao et al.’s findings. Our benchmark study on four ML pipelines revealed consistently low performance across all configurations. Our study failed to replicate original findings, suggesting poor model performance and questioning predictive value of radiomics features in classifying PD-L1 expression from PET/CT imaging. These results highlight challenges in replicating radiomics-based ML models and stress the need for rigorous validation.