CT-scout based, semi-automated vertebral morphometry after digital image enhancement

Abstract

IntroductionRadiographic diagnosis of osteoporotic vertebral fracture is necessary to reduce its substantial associated morbidity. Computed tomography (CT) scout has recently been demonstrated as a reliable technique for vertebral fracture diagnosis. Software assistance may help to overcome some limitations of that diagnostics. We aimed to evaluate whether digital image enhancement improved the capacity of one of the existing software to detect fractures semi-automatically. MethodsCT scanograms of patients suffering from osteoporosis, with or without vertebral fractures were analyzed. The original set of CT scanograms were triplicated and digitally modified to improve edge detection using three different techniques: SHARPENING, UNSHARP MASKING, and CONVOLUTION. ResultsThe manual morphometric analysis identified 1485 vertebrae, 200 of which were classified as fractured. Unadjusted morphometry (AUTOMATED with no digital enhancement) found 63 fractures, 33 of which were true positive (i.e., it correctly identified 52% of the fractures); SHARPENING detected 57 fractures (30 true positives, 53%); UNSHARP MASKING yielded 30 (13 true positives, 43%); and CONVOLUTION found 24 fractures (9 true positives, 38%). The intra-reader reliability for height ratios did not significantly improve with image enhancement (kappa ranged 0.22–0.41 for adjusted measurements and 0.16–0.38 for unadjusted). Similarly, the inter-reader agreement for prevalent fractures did not significantly improve with image enhancement (kappa 0.29–0.56 and −0.01 to 0.23 for adjusted and unadjusted measurements, respectively). ConclusionsOur results suggest that digital image enhancement does not improve software-assisted vertebral fracture detection by CT scout.