# Artery-vein Segmentation on UNAF external (test)

Source: [Artery-vein Segmentation on UNAF external (test)](<https://www.sota2.com/research/sota/artery-vein-segmentation-on-unaf-external-test>)

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

Data updated: 2026-02-26T05:40:57.130Z

Evaluation of artery and vein segmentation performance on the UNAF external test set, reporting Dice scores for both vessel types.

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 | Artery/Vein Segmentation |
| Dataset (including any stated split) | UNAF external (test) |
| Metric | Dice (Artery) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Dice (Artery)](<https://www.sota2.com/research/sota/artery-vein-segmentation-on-unaf-external-test.md?metric=Dice%20(Artery)>): Higher is better; unit: PERCENT.

- [Dice (Vein)](<https://www.sota2.com/research/sota/artery-vein-segmentation-on-unaf-external-test.md?metric=Dice%20(Vein)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Dice (Artery) | Result date | Report paper |
| --- | --- | --- | --- |
| LUNet | 73.31 | Not recorded | 68fa70961e209131cea4c04f |
| VC-Net | 68.71 | Not recorded | 68fa70961e209131cea4c04f |
| BFN | 68.01 | Not recorded | 68fa70961e209131cea4c04f |
| BFN\* | 64.13 | Not recorded | 68fa70961e209131cea4c04f |

### LUNet

Dice (Artery): 73.31. Result ID: 69914ecc3a6c3148490735fe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70961e209131cea4c04f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70961e209131cea4c04f.md>)

Recorded evaluation configuration: {"Training Dataset":"UZLF-train"}. This record does not assert independent reproduction.

### VC-Net

Dice (Artery): 68.71. Result ID: 69914ecc3a6c3148490735fd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70961e209131cea4c04f.md>)

Recorded evaluation configuration: {"Training Dataset":"UZLF-train"}. This record does not assert independent reproduction.

### BFN

Dice (Artery): 68.01. Result ID: 69914ecc3a6c3148490735fc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70961e209131cea4c04f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b601e209131cea2dd58.md>)

[Implementation](<https://github.com/rmaphoh/Learning-AVSegmentation>)

Recorded evaluation configuration: {"Training Dataset":"UZLF-train"}. This record does not assert independent reproduction.

### BFN\*

Dice (Artery): 64.13. Result ID: 69914ecc3a6c3148490735fb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70961e209131cea4c04f.md>)

Recorded evaluation configuration: {"Pre-trained":"Original authors' work"}. This record does not assert independent reproduction.

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