What question did this study set out to answer?

This study aims to develop a deep learning radiomics-based method to predict PD-L1 expression in non-small cell lung cancer.

April 11, 2025Scientific ReportsOpen Access

Predicting PD-L1 status in NSCLC patients using deep learning radiomics based on CT images

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial predicts PD-L1 expression in NSCLC patients, suggesting a tool for personalized treatment decisions.

This study aims to develop a deep learning radiomics-based method to predict PD-L1 expression in non-small cell lung cancer.
Data from 352 NSCLC patients were analyzed for PD-L1 expression.
Deep learning features were extracted from semi-automatically segmented tumor regions on CT images.
Seven algorithms were evaluated for model performance, including an integrated model with clinical data.
The DLR model achieved an AUC of 0.85 (95% CI, 0.82-0.88), sensitivity of 0.80, and specificity of 0.73 for predicting PD-L1 status.
The integrated model performed better, with an AUC of 0.91 (95% CI, 0.87-0.95), sensitivity of 0.85, and specificity of 0.75.

Lu et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark