Quantitative vertebral fracture detection on DXA images using shape and appearance models.

RATIONALE AND
OBJECTIVES: Current quantitative morphometric methods of vertebral fracture detection lack specificity, particularly with mild fractures. We use more detailed shape and texture information to develop quantitative classifiers.
MATERIALS AND METHODS: The detailed shape and appearance of vertebrae on 360 lateral dual energy x-ray absorptiometry scans were statistically modeled, thus producing a set of shape and appearance parameters for each vertebra. The vertebrae were given a "gold standard" classification using a consensus reading by two radiologists. Linear discriminants were trained on the vertebral shape and appearance parameters.
RESULTS: The appearance-based classifiers gave significantly better specificity than shape-based methods in all regions of the spine (overall specificity 92% at a sensitivity of 95%), while using the full shape parameters slightly improved specificity in the thoracic spine compared with using three standard height ratios. The main improvement was in the detection of mild fractures. Performance varied over different regions of the spine. False-positive rates at 95% sensitivity for the lumbar, mid-thoracic (T12-T10) and upper thoracic (T9-T7) regions were 2.9%, 14.6%, and 5.5%, respectively, compared with 6.4%, 32.6%, and 21.1% for three-height morphometry.
CONCLUSION: The appearance and shape parameters of statistical models could provide more powerful quantitative classifiers of osteoporotic vertebral fracture, particularly mild fractures. False positive rates can be substantially reduced at high sensitivity by using an appearance-based classifier, because this can better distinguish between mild fractures and some kinds of non-fracture shape deformities.