Diagnosis of osteoporosis: visual assessment on conventional versus digital radiographs.

In many radiological departments conventional radiography has been replaced by digital radiography. Therefore, the purpose of this study was to analyze the visual detection of osteopenia/osteoporosis with both digital and conventional radiographs. In 286 patients we retrospectively evaluated radiographs of the lumbar spine in two planes. One hundred twenty-eight patients had conventional and 158 patients had digital radiographs. Patients with pre-existing vertebral fractures were excluded. Four experienced musculoskeletal radiologists blinded to the values of DXA and to the patients' ages assessed independently from each other whether the bone density of the lumbar spines was normal or decreased. The results of dual X-ray absorptiometry served as the standard of reference. The threshold value for the diagnosis of osteopenia was a T-score less than -1 SD according to the WHO classification of osteoporosis. Sensitivity/specificity was 86%/36% for conventional and 72%/47% for digital radiographs. The overall diagnostic accuracy was 68% for conventional and 64% for digital radiographs. Eighty percent of the patients with osteopenia and 96% of the patients with osteoporosis were correctly assessed as true positive on conventional radiographs and 65% (osteopenia) and 82% (osteoporosis) on digital radiographs. Interobserver agreement was markedly lower for digital (35%) than for conventional radiographs (73%). However, the differences were not statistically significant. There is no major difference in diagnostic accuracy in the assessment of osteopenia/osteoporosis using digital and conventional radiographs, respectively. However, the high interobserver variance on digital radiographs indicates that visual assessment of osteoporosis/osteopenia is problematic, which may be due to image processing and postprocessing algorithms that manipulate the visual aspect of bone density.