# Vertebra Identification on 2118 spine dataset full (val)

Source: [Vertebra Identification on 2118 spine dataset full (val)](<https://www.sota2.com/research/sota/vertebra-identification-on-2118-spine-dataset-full-val>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:46:57.837Z

Evaluation of model performance on identifying vertebrae using the validation split of the 2118 spine dataset, measured by identification rate and dmean.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Vertebra Identification |
| Dataset (including any stated split) | 2118 spine dataset full (val) |
| Metric | Identification Rate |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Identification Rate](<https://www.sota2.com/research/sota/vertebra-identification-on-2118-spine-dataset-full-val.md?metric=Identification%20Rate>): Higher is better; unit: PERCENT.

- [Mean Distance Error (dmean)](<https://www.sota2.com/research/sota/vertebra-identification-on-2118-spine-dataset-full-val.md?metric=Mean%20Distance%20Error%20(dmean)>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Identification Rate | Result date | Report paper |
| --- | --- | --- | --- |
| GNN | 0.9719 | Not recorded | 68fa70391e209131cea49b25 |
| GNN | 0.9691 | Not recorded | 68fa70391e209131cea49b25 |
| Hidden Markov Model | 0.9429 | Not recorded | 68fa70391e209131cea49b25 |

### GNN

Identification Rate: 0.9719. Result ID: 699124b93a6c314849060094.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70391e209131cea49b25.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70391e209131cea49b25.md>)

Recorded evaluation configuration: {"Architecture":"Joint node/edge"}. This record does not assert independent reproduction.

### GNN

Identification Rate: 0.9691. Result ID: 699124b93a6c314849060095.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70391e209131cea49b25.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70391e209131cea49b25.md>)

Recorded evaluation configuration: {"Architecture":"Node only"}. This record does not assert independent reproduction.

### Hidden Markov Model

Identification Rate: 0.9429. Result ID: 699124b93a6c314849060096.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70391e209131cea49b25.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
