What question did this study set out to answer?

The study aims to create and validate a predictive model for occult lymph node metastasis (OLNM) in localized non-small cell lung cancer (NSCLC).

Development and external validation of a FDG PET-based radiomics model predicting occult lymph node metastasis in non-small cell lung cancer patients

View Full Paper

Ask AI

Bookmark

Authors

Develops and validates a radiomics model predicting lymph node metastasis in NSCLC, suggesting improved clinical decisions.

The study aims to create and validate a predictive model for occult lymph node metastasis (OLNM) in localized non-small cell lung cancer (NSCLC).
Developed two models (Model PET and Model Combined) using radiomics features from a monocentric cohort of localized NSCLC patients.
Validated the models on an external cohort and assessed in a different cohort undergoing stereotactic body radiotherapy.
Used multilayer perceptron to predict OLNM from FDG PET.
Assessed regional relapse free survival as a surrogate for OLNM.
Model PET achieved an AUC of 0.92 in the training cohort and an AUC of 0.73 in the external cohort, indicating good predictive performance.
Model Combined reached high accuracy in the training cohort but lower in the external cohort.
Predicted OLNM risk from Model PET correlated with worse regional relapse free survival (HR 1.60, p = 0.04).
Model Combined did not show significant associations with survival outcomes.

Bourbonne et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark