Local Area Cartilage Segmentation: A Semiautomated Novel Method of Measuring Cartilage Loss in Knee Osteoarthritis
Bibliographic record
Abstract
OBJECTIVE: To assess the responsiveness and reader time of a novel semiautomated tool to detect knee cartilage loss over 2 years in subjects with knee osteoarthritis. METHODS: A total of 122 subjects from the Osteoarthritis Initiative progression cohort were selected. A reader used the software method to segment cartilage on double-echo steady-state sequence scans in the medial compartment of the femur from the baseline and 24-month visits. Change in cartilage volume (ΔV) was measured at a fixed weight-bearing (WB) location with respect to the 3-dimensional coordinate system based on cylindrical coordinates. Change was measured for 5 regions of varying WB surface area centered on the fixed point. The average change (ΔV), the SD of ΔV, and the standardized response mean (SRM) are reported. RESULTS: The SRM was −0.52 for the largest region and decreased in magnitude as smaller regions of cartilage were probed. The average evaluation time was <20 minutes per knee compartment, split approximately evenly between a technician and a trained reader. CONCLUSION: The results establish that measurement of cartilage loss in a local region can be done efficiently and that the resultant measures are responsive to loss of cartilage over time. The coordinate system can potentially be used to objectively examine and establish a consistent location for all knees that is most responsive to change in cartilage volume. This technique can provide rapidly an objective quantitative measure of cartilage loss and could substantially reduce study costs for large trials and data sets.
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 | 0.003 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".