Vertebral labeling on MRI using deep learning techniques
Bibliographic record
Abstract
For the diagnosis and monitoring of various diseases in the spine and the central nervous system, the detection and labeling of vertebrae in magnetic resonance imaging (MRI) is useful. Although several automatic methods for the detection and labeling of vertebrae have been developed, this is still an open task in which many improvements can be made. One way to detect the vertebra is to focus on the intervertebral discs (IVD), which are natural spacers between vertebrae. In this work, we present a set of convolutional networks (CNN) that perform regression for the detection and labeling of the IVD. The entry for each of the CNNs is the midsagittal plane image of the acquired volume. Each CNN is in charge of detecting one intervertebral disc, so the labeling is done implicitly. The output of each CNN is the coordinate (x, y) of the located IVD. We have done the training with the first 6 IVD (C2-C3 to C7-T1) using a total of 631 images with a pixel resolution of 1mm x 1mm. The mean error is between 2.98.mm and 4.33mm, the standard deviation range is between ±2.45 and ±3.45. Such results are competitive with the state of the art but require significantly less computational resources (estimated 2x) than other architectures based on fully convolutional networks.
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 | 0.000 | 0.001 |
| 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 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
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".