Using machine learning to automatically measure axial vertebral rotation on radiographs in adolescents with idiopathic scoliosis
Bibliographic record
Abstract
Adolescent idiopathic scoliosis is a 3D lateral spinal curvature coupled with axial vertebral rotation (AVR). Measuring AVR during clinic is important because it affects treatment options and predicts the risk of scoliosis progression. However, manual measurements are time consuming and have high inter-rater and intra-rater errors. This study aimed to develop a machine learning algorithm based on convolutional neural networks (CNNs) to automatically calculate AVR on posteroanterior radiographs using three different segmentations including spinal column, individual vertebra, and pedicles. Separate labeling and training processes were performed on each of the developed segmentation algorithms. The final machine learning software was tested on 221 vertebrae from 17 spinal radiographs. An experienced rater with over 25 years of experience measured the 221 vertebral rotations manually. By comparing the manual and the fully automatic measurements, 81% (178/221) of the automatic measurements were within the clinical acceptance error (±5°). The mean absolute difference and the standard deviation between the manual and automatic measurements was 4.3° ± 5.7°. Based on the Bland-Altman plot, the manual and automatic measurements had a strong correlation and no bias. The error did not relate to the severity of the rotation. This method is fully automatic, and the result is comparable to others.
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 | 0.001 | 0.007 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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".