The effect of file type and DXA protocol on an image processing fracture risk prediction tool

Osteoporosis, a common bone disease in older adults, is associated with low bone mineral density (BMD) and an increased risk of fractures. While fracture risk is often assessed using T-scores derived from dual-energy X-ray absorptiometry (DXA) scans, these measures are not fully effective in identifying individuals at greatest risk. To address this, a Statistical Shape and Appearance Modeling (SSAM) tool was previously developed to analyze femur shape and BMD distribution and demonstrated superior fracture risk prediction compared to T-scores using hip DXA scans exported in JPG format. The present study aimed to evaluate whether changes in DXA-imaging protocol (hip protocol vs. High-Definition Instant Vertebral Assessment (IVA-HD)) may influence the image and the SSAM tool's fracture risk predictions. The effect of image file type (JPG vs. PNG) was also explored, as native formats such as Digital Imaging and Communications in Medicine (DICOM) cannot be readily exported or saved in large databases. DXA scans from 36 subjects and seven cadaveric femurs were analyzed across four imaging conditions (file types and imaging protocols). Structural Similarity Index Measures (SSIM) quantified image differences, and Bland-Altman plots assessed agreement in fracture risk predictions. Minimal differences were found in SSAM tool outputs across protocols and file types. Higher-resolution scans (IVA-HD) and lossless file types (PNG) did not improve the accuracy of risk predictions compared to the standard hip protocol in JPG format. These findings suggest that the SSAM tool is robust to variations in imaging conditions, supporting its use with standard DXA imaging protocols and file formats.