Incidental vertebral fracture prediction using neuronal network-based automatic spine segmentation and volumetric bone mineral density extraction from routine clinical CT scans

• Published in: Frontiers in endocrinology (Lausanne) Vol. 14; p. 1207949
• Main Authors: Bodden, Jannis, Dieckmeyer, Michael, Sollmann, Nico, Burian, Egon, Rühling, Sebastian, Löffler, Maximilian T, Sekuboyina, Anjany, El Husseini, Malek, Zimmer, Claus, Kirschke, Jan S, Baum, Thomas
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Media S.A 17.07.2023
• Subjects: artificial intelligence; Bayes Theorem; bone density; Bone Density - physiology; Endocrinology; Female; Humans; Male; Middle Aged; osteoporosis; osteoporotic fractures; Osteoporotic Fractures - diagnostic imaging; Osteoporotic Fractures - epidemiology; Osteoporotic Fractures - etiology; Prevalence; Retrospective Studies; Spinal Fractures - diagnostic imaging; Spinal Fractures - epidemiology; tomography; Tomography, X-Ray Computed - methods; x-ray computed; osteoporosis; osteoporotic fractures; tomography; artificial intelligence; bone density; x-ray computed
• ISSN: 1664-2392; 1664-2392
• DOI: 10.3389/fendo.2023.1207949

To investigate vertebral osteoporotic fracture (VF) prediction by automatically extracted trabecular volumetric bone mineral density (vBMD) from routine CT, and to compare the model with fracture prevalence-based prediction models. This single-center retrospective study included patients who underwent two thoraco-abdominal CT scans during clinical routine with an average inter-scan interval of 21.7 ± 13.1 months (range 5-52 months). Automatic spine segmentation and vBMD extraction was performed by a convolutional neural network framework (anduin.bonescreen.de). Mean vBMD was calculated for levels T5-8, T9-12, and L1-5. VFs were identified by an expert in spine imaging. Odds ratios (ORs) for prevalent and incident VFs were calculated for vBMD (per standard deviation decrease) at each level, for baseline VF prevalence (yes/no), and for baseline VF count (n) using logistic regression models, adjusted for age and sex. Models were compared using Akaike's and Bayesian information criteria (AIC & BIC). 420 patients (mean age, 63 years ± 9, 276 males) were included in this study. 40 (25 female) had prevalent and 24 (13 female) had incident VFs. Individuals with lower vBMD at any spine level had higher odds for VFs (L1-5, prevalent VF: OR,95%-CI,p: 2.2, 1.4-3.5,p=0.001; incident VF: 3.5, 1.8-6.9,p<0.001). In contrast, VF status (2.15, 0.72-6.43,p=0.170) and count (1.38, 0.89-2.12,p=0.147) performed worse in incident VF prediction. Information criteria revealed best fit for vBMD-based models (AIC vBMD=165.2; VF status=181.0; count=180.7). VF prediction based on automatically extracted vBMD from routine clinical MDCT outperforms prediction models based on VF status and count. These findings underline the importance of opportunistic quantitative osteoporosis screening in clinical routine MDCT data.