Prediction of acute versus chronic osteoporotic vertebral fracture using radiomics-clinical model on CT.

PURPOSE

This paper aims to use radiomics-clinical analysis based on CT imaging to distinguish between acute and chronic osteoporotic vertebral fractures.

METHOD

A total of 147 patients who underwent both dual-energy X-ray absorptiometry (DEXA), CT and MRI of the spine were analyzed retrospectively. The patients were assigned to either a training cohort (n = 103) or a validation cohort (n = 44). The radiomics model and combined nomogram model were established by multivariate logistic regression analysis. The predictive performance was assessed with receiver operating characteristic (ROC) curve.

RESULTS

Fourteen radiomic features based on spine CT images were constructed to distinguish acute versus chronic osteoporotic vertebral fractures, and its differentialperformance was good with an area under the curve (AUC) of 0.90 (95% CI, 0.84-0.95) in the training cohort and 0.82 (95% CI, 0.69-0.94) in the validation cohort. Based on the radiomic signature and clinical fracture line feature, a combined nomogram was developed and showed excellent differential ability with highest AUC of 0.93 (95 %CI,0.88-0.98) in the training cohort and 0.86 (95 %CI,0.73-0.98) in the validation cohort, which performed better than the clinical model significantly only.

CONCLUSIONS

A quantitative nomogram based on clinical fracture line feature and radiomic features of CT images can be used to distinguish acute and chronic osteoporotic vertebral fractures with excellent predictive ability, which can be served as a potential decision support tool to assist clinicians in evaluating the phase of vertebral fractures timely, especially in situation where spine MRI was not available for patient.