Advancing osteoporosis opportunistic screening: multicenter validation of a deep learning algorithm using abdominal CT scans.
Authors
Affiliations (12)
Affiliations (12)
- Departamento de Diagnóstico por Imagem, Federal University of São Paulo, São Paulo, Brazil. [email protected].
- Instituto de Radiologia, Hospital das Clínicas da Faculdade de Medicina da Universidade de São Paulo, São Paulo, Brazil. [email protected].
- Bunkerhill Health, San Francisco, USA. [email protected].
- Department of Radiology, University of North Carolina at Chapel Hill, Chapel Hill, USA.
- Departamento de Diagnóstico por Imagem, Federal University of São Paulo, São Paulo, Brazil.
- Dasa, São Paulo, Brazil.
- Bunkerhill Health, San Francisco, USA.
- Department of Radiology, University of Alabama at Birmingham, Birmingham, USA.
- Department of Radiology, University Hospitals Cleveland Medical Center, Cleveland, USA.
- Case Western Reserve University, Cleveland, USA.
- Department of Radiology, MedStar Georgetown University Hospital, Washington, DC, USA.
- Department of Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, USA.
Abstract
To develop and do multicenter validation on an algorithm that screens for osteoporosis from abdominal CTs. 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. 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/cm<sup>2</sup>). 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. We developed and performed a multicenter validation of a DL model for osteoporosis prediction on CT.