Fully automated system for the quantification of human osteoarthritic knee joint effusion volume using magnetic resonance imaging
Bibliographic record
Abstract
INTRODUCTION: Joint effusion is frequently associated with osteoarthritis (OA) flare-up and is an important marker of therapeutic response. This study aimed at developing and validating a fully automated system based on magnetic resonance imaging (MRI) for the quantification of joint effusion volume in knee OA patients. METHODS: MRI examinations consisted of two axial sequences: a T2-weighted true fast imaging with steady-state precession and a T1-weighted gradient echo. An automated joint effusion volume quantification system using MRI was developed and validated (a) with calibrated phantoms (cylinder and sphere) and effusion from knee OA patients; (b) with assessment by manual quantification; and (c) by direct aspiration. Twenty-five knee OA patients with joint effusion were included in the study. RESULTS: The automated joint effusion volume quantification was developed as a four stage sequencing process: bone segmentation, filtering of unrelated structures, segmentation of joint effusion, and subvoxel volume calculation. Validation experiments revealed excellent coefficients of variation with the calibrated cylinder (1.4%) and sphere (0.8%) phantoms. Comparison of the OA knee joint effusion volume assessed by the developed automated system and by manual quantification was also excellent (r = 0.98; P < 0.0001), as was the comparison with direct aspiration (r = 0.88; P = 0.0008). CONCLUSIONS: The newly developed fully automated MRI-based system provided precise quantification of OA knee joint effusion volume with excellent correlation with data from phantoms, a manual system, and joint aspiration. Such an automated system will be instrumental in improving the reproducibility/reliability of the evaluation of this marker in clinical application.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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".