Advancing osteoporosis opportunistic screening: multicenter validation of a deep learning algorithm using abdominal CT scans

Clinical Snapshot

Key Findings

• P Value: Not explicitly reported for primary outcome

• Effect Size: AUC 0.82 (external validation)

• Primary Outcome: Diagnostic accuracy for osteoporosis detection using CT-derived MSMA

• Nnt Or Sensitivity: Sensitivity 79% (95% CI: 61-90%), Specificity 81% (95% CI: 76-84%)

• Confidence Interval: 95% CI: 0.74-0.89

Clinical Application

Requires implementation of deep learning infrastructure but uses existing CT scans without additional radiation Could integrate with existing osteoporosis prevention programs under PBS item 12306. Aligns with RACGP guidelines for opportunistic screening in at-risk populations Adults undergoing routine abdominal CT scans, particularly those over 50 years

Abstract

OBJECTIVES: To develop and do multicenter validation on an algorithm that screens for osteoporosis from abdominal CTs. METHODS: This is a diagnostic accuracy study with retrospective data from January 2022 to July 2022 consisting of two steps: a segmentation step of the lumbar vertebral bodies, involving outpatient non-contrast abdominal CTs from Diagnósticos da América S/A (Dasa), and a multicenter validation step incorporating data from four additional institutions. The segmentation employed a 2D UNet with a ResNet34 backbone. We determined the Pearson correlation coefficient (r) between the mean of the slices' mean attenuations (MSMA) on CT scans against the bone mineral density (BMD) on recent DEXA scans, calculated AUCs and performance metrics for osteoporosis prediction, including 95% confidence intervals, and evaluated calibration plots. RESULTS: The multicenter validation included 504 participants (median age, 66 years, interquartile range 56-72; 388 women). A linear regression analysis showed an r of 0.62 (95% CI, 0.56-0.67) between MSMA (HU) and BMD (g/cm2). The AUCs (95% CI) for distinguishing between normal and osteoporosis were 0.96 (0.89, 1.0) for the internal dataset and 0.82 (0.74, 0.89) for the external dataset, and the performance metrics (95% CI), for a globally optimized threshold of 202.6 HU, were 100% sensitivity (44, 100) and 91% specificity (84, 95) for internal data and 79% sensitivity (61, 90) and 81% specificity (76, 84) for external sites. MSMA was independently associated with osteoporosis on a mixed-effects logistic regression analysis. The model showed good calibration, with Brier score of 0.054. CONCLUSION: We developed and performed a multicenter validation of a DL model for osteoporosis prediction on CT.

References

1. 1.Sarquis Serpa, A., Straus Takahashi, M., Júdice de Mattos Farina, E. M., Bennett, S., Khandwala, N., Major, M., Paparian, J., Garozzo Velloni, F., Rothenberg, S., Kayat Bittencourt, L., Filice, R. W., Mongan, J., & Campos Kitamura, F. (2026). Advancing osteoporosis opportunistic screening: multicenter validation of a deep learning algorithm using abdominal CT scans. Abdominal Radiology. https://doi.org/10.1371/journal.pone.0290289