The effect of file type and DXA protocol on an image processing fracture risk prediction tool
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.017 | 0.120 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".