AI-derived vertebral bone density and paraspinal muscle-fat metrics improve vertebral fracture detection in breast cancer survivors on routine CT

In breast cancer survivors, AI-derived vertebral bone density (vBMD) and paraspinal muscle-fat ratio on routine CT helped identify moderate-severe vertebral fractures. AI-vBMD AUC 0.738, adding muscle-fat ratio improved AUC to 0.786, full model AUC 0.828.

• In 275 breast cancer survivors, moderate-to-severe vertebral compression fractures were present in 27.3% (75 patients).
• AI-vBMD alone gave AUC 0.738 for fracture identification, significantly outperforming HU-vBMD (AUC 0.714; p < 0.001).
• Adding paraspinal intermuscular adipose tissue (IMAT) ratio to AI-vBMD improved AUC to 0.786; a full model with clinical covariates achieved AUC 0.828 (95% CI, 0.778–0.878).

Automated summary

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