Performance of statistical models of shape and appearance for semiautomatic segmentations of spinal vertebrae T4–L4 on digitized vertebral fracture assessment images

Abstract

Background contextDespite its clinical importance, accurate identification of vertebral fractures is problematic and time-consuming. There is a recognized need to improve the detection of vertebral fractures so that appropriate high-risk patients can be selected to initiate clinically beneficial therapeutic interventions. PurposeTo develop and evaluate semiautomatic algorithms for detailed annotation of vertebral bodies from T4 to L4 in digitized lateral spinal dual-energy X-ray absorptiometry (DXA) vertebral fracture assessment (VFA) images. Study designUsing lateral spinal DXA VFA images from subjects imaged at University Hospital fracture liaison service, image algorithms were developed for semiautomatic detailed annotation of vertebral bodies from T4 to L4. Patient sampleTwo hundred one women aged 50 years or older with nonvertebral fractures. Outcome measuresAlgorithm accuracy and precision. MethodsStatistical models of vertebral shape and appearance from T4 to L4 were constructed using VFA images from 130 subjects. The resulting models form a part of an algorithm for performing semiautomatic detailed annotation of vertebral bodies from T4 to L4. Algorithm accuracy and precision were evaluated on a test-set of 71 independent images. ResultsOverall accuracy was 0.72 mm (3.00% of vertebral height) and overall precision was 0.26 mm (1.11%) for point-to-line distance. Accuracy and precision were best on normal vertebrae (0.65 mm [2.67%] and 0.21 mm [0.90%], respectively) and mild fractures (0.78 mm [3.18%] and 0.32 mm [1.39%], respectively), but accuracy and precision errors were higher for moderate (1.07 mm [4.66%] and 0.48 mm [2.15%], respectively) and severe fractures (2.07 mm [9.65%] and 1.10 mm [5.09%], respectively). Accuracy and precision results for the algorithm were comparable with other reported results in the literature. ConclusionsThis semiautomatic image analysis had high overall accuracy and precision on normal vertebrae and mild fractures, but performed less well in moderate and severe fractures. It is, therefore, a useful tool to identify normality of vertebral shape and to identify mild fractures.