Making Every CT Count: Automated Body Composition Analysis for Clinical Use in COPD and Beyond
Bibliographic record
Abstract
Background: Muscle loss in COPD worsens prognosis and increases morbidity and hospitalizations. While diagnostic CT scans contain valuable unused body composition (BC) data, current assessment methods are time-consuming and impractical for routine use, highlighting the need for automated solutions. Aim: To evaluate the agreement between a fully automated and an expert-driven semi-automated segmentation method for BC analysis in thoracic and abdominal CT scans. Methods: CT images from trauma patients without chronic disease were retrospectively analyzed. One axial slice per vertebral level (T2–L5) was segmented using a semi-automated method with manual corrections (viking Slice) and a fully automated method (DAFS Express). HU thresholds, based on Alberta protocol, muscle(MUS), visceral(VAT), intermuscular(IMAT) and subcutaneous fat (SAT). VAT from T2–T10 was excluded due to the lack of manual segmentation. Dice scores assessed agreement between methods. Results: 21patients (11 males; median age 29 years) were included, with 332 images analyzed. DAFS processed images: average of 18 seconds/ image (total 1 hour 37 minutes) compared to 1–9 minutes/image for manual segmentation. erj;66/suppl_69/PA977/TB1 T1 TB1 Table 1 Mean Dice score (95% confidence interval) Number of images R1 vs R2 DAFS vs R1 DAFS vs R2 MUS 335 .958 (CI .957; .960) .943 (CI 940; .946) .943 (CI .940; .946) VAT 144 .972 (CI.961; .982) .960 (CI .947; .974) .965 (CI .956; .974) SAT 335 .992 (CI .990; .993) .926 (CI .922; .931) .922 (CI .917; .928) Conclusion: The automated method showed excellent agreement with the semi-automated method, supporting its use as a rapid reproducible tool for BC analysis to aid early muscle loss detection in COPD and other diseases
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 | 0.002 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.024 | 0.009 |
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".