Automatic opportunistic osteoporosis screening in routine CT: improved prediction of patients with prevalent vertebral fractures compared to DXA

Abstract

Objectives To compare spinal bone measures derived from automatic and manual assessment in routine CT with dual energy X-ray absorptiometry (DXA) in their association with prevalent osteoporotic vertebral fractures using our fully automated framework (https://anduin.bonescreen.de) to assess various bone measures in clinical CT. Methods We included 192 patients (141 women, 51 men; age 70.2 ± 9.7 years) who had lumbar DXA and CT available (within 1 year). Automatic assessment of spinal bone measures in CT included segmentation of vertebrae using a convolutional neural network (CNN), reduction to the vertebral body, and extraction of bone mineral content (BMC), trabecular and integral volumetric bone mineral density (vBMD), and CT-based areal BMD (aBMD) using asynchronous calibration. Moreover, trabecular bone was manually sampled (manual vBMD). Results A total of 148 patients (77%) had vertebral fractures and significantly lower values in all bone measures compared to patients without fractures (p ≤ 0.001). Except for BMC, all CT-based measures performed significantly better as predictors for vertebral fractures compared to DXA (e.g., AUC = 0.885 for trabecular vBMD and AUC = 0.86 for integral vBMD vs. AUC = 0.668 for DXA aBMD, respectively; both p < 0.001). Age- and sex-adjusted associations with fracture status were strongest for manual vBMD (OR = 7.3, [95%] CI 3.8–14.3) followed by automatically assessed trabecular vBMD (OR = 6.9, CI 3.5–13.4) and integral vBMD (OR = 4.3, CI 2.5–7.6). Diagnostic cutoffs of integral vBMD for osteoporosis (< 160 mg/cm3) or low bone mass (160 ≤ BMD < 190 mg/cm3) had sensitivity (84%/41%) and specificity (78%/95%) similar to trabecular vBMD. Conclusions Fully automatic osteoporosis screening in routine CT of the spine is feasible. CT-based measures can better identify individuals with reduced bone mass who suffered from vertebral fractures than DXA. Key Points • Opportunistic osteoporosis screening of spinal bone measures derived from clinical routine CT is feasible in a fully automatic fashion using a deep learning-driven framework (https://anduin.bonescreen.de). • Manually sampled volumetric BMD (vBMD) and automatically assessed trabecular and integral vBMD were the best predictors for prevalent vertebral fractures. • Except for bone mineral content, all CT-based bone measures performed significantly better than DXA-based measures. • We introduce diagnostic thresholds of integral vBMD for osteoporosis (< 160 mg/cm3) and low bone mass (160 ≤ BMD < 190 mg/cm3) with almost equal sensitivity and specificity compared to conventional thresholds of quantitative CT as proposed by the American College of Radiology (osteoporosis < 80 mg/cm3).

Epidemiology and reporting of osteoporotic vertebral fractures in patients with long-term hospital records based on routine clinical CT imaging

“…The spectrum of classifications with a focus on morphometry alone comprises at least seven methods, with more or less overlap in their definitions [15]. We chose the semi-quantitative method by Genant to classify VFs [21], because we had sufficient experience with its application on sagittal CT reformation [18,[26][27][28][29][30] and it is the most widely used tool in population studies [15,31].…”

Texture Analysis Using CT and Chemical Shift Encoding-Based Water-Fat MRI Can Improve Differentiation Between Patients With and Without Osteoporotic Vertebral Fractures

“…Although vertebral body segmentation as well as texture analysis are not part of the clinical routine, approaches are feasible without considerable computational efforts. In detail, CT image segmentation and vBMD extraction are already established, automated, computationally optimized, and their computational effort can therefore be considered negligible in comparison to the remaining tasks (when implementing a pipeline such as the herein used CNN-based framework for vertebral body labeling and segmentation with parameter extraction) (43)(44)(45). Details on the computational efficiency of the water-fat separation for generating PDFF and T2* maps have been reported previously for a similar workflow (49).…”

“…From PACS, images were transferred to our in-house developed, convolutional neural network (CNN)-based framework (https:// anduin.bonescreen.de) (Figures 1 and 2) (43)(44)(45). This tool identifies and labels each vertebra in an automated process, followed by creating corresponding segmentation masks for each vertebra as well as its subregions.…”

“…This tool identifies and labels each vertebra in an automated process, followed by creating corresponding segmentation masks for each vertebra as well as its subregions. Furthermore, it adjusts for the used scanner, scanning parameters, and contrast media (if administered during imaging) to asynchronously convert measured HU into vBMD (43)(44)(45).…”

Automated detection of the contrast phase in MDCT by an artificial neural network improves the accuracy of opportunistic bone mineral density measurements

“…Vertebrae at the levels of L1-L3 that had a fracture grade greater than 1 were excluded from further BMD assessment (n = 22). BMD values were automatically extracted from the segmentations masks of the trabecular compartment of vertebral bodies, and scanner-specific HU-to-BMD conversion equations previously calculated with density reference phantoms (QRM) were applied [28]. BMD values were averaged over non-fractured lumbar vertebrae L1-L3 and linear correction equations calculated in the training set were applied for each contrast phase.…”