# Opportunistic Osteoporosis Screening in Breast Cancer Using AI-Derived Vertebral BMD from Routine CT: Validation Against QCT and Multivariable Diagnostic Modeling

## TL;DR

AI can extract bone density from routine CT scans to screen for osteoporosis in breast cancer patients, offering a reliable and valuable diagnostic tool.

## Contribution

Validated AI-derived vertebral BMD from routine CT as a reliable and clinically useful biomarker for osteoporosis screening in breast cancer patients.

## Key findings

- AI-derived vertebral BMD showed strong correlation with QCT-derived BMD (r = 0.98).
- AI-vBMD integration into clinical models significantly improved diagnostic performance (AUC 0.988 vs. 0.879).
- AI-vBMD alone achieved excellent discrimination for osteoporosis (AUC = 0.986).

## Abstract

Background/Objectives: Breast cancer survivors face elevated risk of treatment-related bone loss, yet routine bone health assessment remains underutilized. Opportunistic bone density extraction from routine CT may address this gap. This study validated AI-derived vertebral bone mineral density (AI-vBMD) from non-contrast thoracoabdominal CT for osteoporosis screening and assessed its diagnostic value beyond clinical variables. Methods: This retrospective study included 332 breast cancer patients; AI-vBMD was successfully extracted in 325 (98%). Quantitative CT (QCT) served as reference standard. Agreement between AI-vBMD and QCT-vBMD was assessed using Pearson correlation, Bland–Altman analysis, and weighted kappa for QCT-defined osteoporosis (<80 mg/cm3). Nested logistic regression models compared a clinical model with and without AI-vBMD. Discrimination [area under the curve (AUC)], calibration, and clinical utility [decision-curve analysis (DCA)] were evaluated. Results: AI-vBMD showed strong correlation with QCT-vBMD (r = 0.98, p < 0.001), minimal bias (mean difference +1.82 mg/cm3), and excellent agreement for osteoporosis classification (weighted κ = 0.90). AI-vBMD alone achieved excellent discrimination for osteoporosis (AUC = 0.986). Integrating AI-vBMD into the clinical model yielded significantly higher diagnostic performance (AUC 0.988 vs. 0.879; p < 0.001) and demonstrated superior net benefit across relevant decision thresholds. Conclusions: AI-derived vertebral BMD from routine CT serves as a reliable QCT-aligned imaging biomarker for opportunistic osteoporosis assessment in breast cancer patients and adds significant incremental diagnostic value beyond clinical information alone.