AI-Driven Opportunistic CT Osteoporosis Screening and Establishment of Normative Values
Listed in
This article is not in any list yet, why not save it to one of your lists.Abstract
Background
Osteoporosis is underdiagnosed and undertreated. Traditional screening methods like dual-energy X-ray absorptiometry have limitations, prompting the exploration of opportunistic screening using CT and artificial intelligence (AI).
Purpose
To develop a reproducible and robust AI-based method to automatically assess spine trabecular attenuation on noncontrast CTs, irrespective of protocol or scanner model used during imaging acquisition, and to establish normative values in a large diverse population.
Methods
An AI-based method was developed to automatically quantify trabecular attenuation using a 3D region of interest (ROI) of the thoracic and lumbar spine on chest, abdomen, or spine CTs, adjusted for different tube voltages and scanner models. Normative values, thresholds for osteoporosis of trabecular attenuation of the thoracic and lumbar spine were established across a diverse population, stratified by age, sex, race, and ethnicity. Differences in trabecular attenuation were assessed using the Mann-Whitney U or the Chi-Square Test.
Results
538,946 CT examinations from 283,499 patients (mean age 65 years ± 15, 51.2% women and 55.5% White), performed on 50 scanner models using six different tube voltages were analyzed. Hounsfield Units at 80 kVp versus 120 kVp differed by 23%, and different scanner models resulted in differences of values by < 10%. Automated ROI placement was validated by manual radiologist review, demonstrating 99% agreement. Mean trabecular attenuation was higher in young women (<50 years) than young men (p<.001) and decreased with age, with a steeper decline in postmenopausal women. In patients older than 50 years, trabecular attention was higher in male than female patients (p<.001). Trabecular attenuation was highest in Blacks, followed by Asians and lowest in Whites (p<.001). The threshold for L1 in diagnosing osteoporosis was 68 HU.
Conclusion
AI-based automated opportunistic osteoporosis screening can identify patients with low bone mineral density that undergo CT scans for clinical purposes on different scanners and protocols.
