Reliability and Accuracy Analysis of a New Semiautomatic Radiographic Measurement Software in Adult Scoliosis
Bibliographic record
Abstract
STUDY DESIGN: Radiographic software measurement analysis in adult scoliosis. OBJECTIVE: To assess the accuracy as well as the intra- and interobserver reliability of measuring different indices on preoperative adult scoliosis radiographs using a novel measurement software that includes a calibration procedure and semiautomatic features to facilitate the measurement process. SUMMARY OF BACKGROUND DATA: Scoliosis requires a careful radiographic evaluation to assess the deformity. Manual and computer radiographic process measures have been studied extensively to determine the reliability and reproducibility in adolescent idiopathic scoliosis. Most studies rely on comparing given measurements, which are repeated by the same user or by an expert user. A given measure with a small intra- or interobserver error might be deemed as good repeatability, but all measurements might not be truly accurate because the ground-truth value is often unknown. Thorough accuracy assessment of radiographic measures is necessary to assess scoliotic deformities, compare these measures at different stages or to permit valid multicenter studies. METHODS: Thirty-four sets of adult scoliosis digital radiographs were measured two times by three independent observers using a novel radiographic measurement software that includes semiautomatic features to facilitate the measurement process. Twenty different measures taken from the Spinal Deformity Study Group radiographic measurement manual were performed on the coronal and sagittal images. Intra- and intermeasurer reliability for each measure was assessed. The accuracy of the measurement software was also assessed using a physical spine model in six different scoliotic configurations as a true reference. RESULTS: The majority of the measures demonstrated good to excellent intra- and intermeasurer reliability, except for sacral obliquity. The standard variation of all the measures was very small: ≤ 4.2° for Cobb angles, ≤ 4.2° for the kyphosis, ≤ 5.7° for the lordosis, ≤ 3.9° for the pelvic angles, and ≤5.3° for the sacral angles. The variability in the linear measurements (distances) was <4 mm. The variance of the measures was 1.7 and 2.6 times greater, respectively, for the angular and linear measures between the inter- and intrameasurer reliability. The image quality positively influenced the intermeasurer reliability especially for the proximal thoracic Cobb angle, T10-L2 lordosis, sacral slope and L5 seating. The accuracy study revealed that on average the difference in the angular measures was < 2° for the Cobb angles, and < 4° for the other angles, except T2-T12 kyphosis (5.3°). The linear measures were all <3.5 mm difference on average. CONCLUSION: The majority of the measures, which were analyzed in this study demonstrated good to excellent reliability and accuracy. The novel semiautomatic measurement software can be recommended for use for clinical, research or multicenter study purposes.
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 | 0.019 | 0.059 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".