Whole-Body Bone Scintigraphy Nomogram for Predicting MDP-Avid Bone Metastases in NSCLC

A radiomics-deep learning nomogram using planar whole-body bone scintigraphy predicted MDP-avid bone metastases in non-small cell lung cancer with an external validation AUC of 0.870 (95% CI 0.840-0.900).

• The radiomics component (Rad-score) was the most influential predictor in the nomogram.
• Significant survival stratification was observed for patients with solitary bone lesions on Kaplan-Meier analysis.
• A research-use-only desktop application was created to facilitate external validation and reproducibility.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.