LAUSR

ObjectiveTo evaluate the clinical applicability of a software tool developed to extract bone textural information from conventional lumbar spine radiographs, and to test it in a subset of postmenopausal women treated for osteoporosis with the fully human monoclonal antibody denosumab.MethodsThe software was developed based on the principles of a fractal model using pixel grey-level variations together with a specific machine-learning algorithm. The obtained dimensionless parameter, termed bone structure value (BSV), was then tested and compared to bone mineral density (BMD) in a sub-cohort of postmenopausal women with osteoporosis who were treated with the monoclonal antibody denosumab, within the framework of a large randomized controlled trial and its open-label extension phase.ResultsAfter 3 years and after 8 years of treatment with denosumab, mean lumbar spine BMD as well as mean lumbar BSV were significantly higher compared to study entry (one-way repeated measures ANOVA for DXA: F = 108.2, p < 0.00001; and for BSV: F = 84.3, p < 0.00001). The overall increase in DXA-derived lumbar spine BMD at year 8 was + 42% (mean ± SD; 0.725 ± 0.038 g/cm2 to 1.031 ± 0.092 g/cm2; p < 0.0001), and the overall increase of BSV was 255% (mean ± SD; 0.076 ± 0.022 to 0.270 ± 0.09, p < 0.0001). Overall, BMD and BSV were significantly correlated (R = 0.51; p < 0.0001).ConclusionsThis pilot study provides evidence that lumbar spine BSV as obtained from conventional radiographs constitutes a useful means for the assessment of bone-specific treatment effects in postmenopausal women with osteoporosis.