# Coronary artery segmentation on ICAS-100 cross-dataset (test)

Source: [Coronary artery segmentation on ICAS-100 cross-dataset (test)](<https://www.sota2.com/research/sota/coronary-artery-segmentation-on-icas-100-cross-dataset-test>)

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

Data updated: 2026-02-26T05:40:22.222Z

Evaluation of coronary artery segmentation performance on the ICAS-100 cross-dataset (test split), reporting metrics such as Dice Similarity Coefficient (DSC) and Average Surface Distance (ASSD).

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 | Coronary artery segmentation |
| Dataset (including any stated split) | ICAS-100 cross-dataset (test) |
| Metric | DSC |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [DSC](<https://www.sota2.com/research/sota/coronary-artery-segmentation-on-icas-100-cross-dataset-test.md?metric=DSC>): Higher is better; unit: PERCENT.

- [ASSD](<https://www.sota2.com/research/sota/coronary-artery-segmentation-on-icas-100-cross-dataset-test.md?metric=ASSD>): Lower is better; unit: SCALAR.

## Recorded results

| Method | DSC | Result date | Report paper |
| --- | --- | --- | --- |
| Ours | 78.74 | Not recorded | 68fa7a0b1e209131cea80c50 |
| VSNet | 75.87 | Not recorded | 68fa7a0b1e209131cea80c50 |
| I2U-Net | 75.76 | Not recorded | 68fa7a0b1e209131cea80c50 |
| nnFormer | 75.62 | Not recorded | 68fa7a0b1e209131cea80c50 |
| 3D-UNet | 73.55 | Not recorded | 68fa7a0b1e209131cea80c50 |

### Ours

DSC: 78.74. Result ID: 698b6ab57a967eddb76e6500.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a0b1e209131cea80c50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a0b1e209131cea80c50.md>)

[Implementation](<https://github.com/d1c2x3/CAseg>)

Recorded evaluation configuration: {"Training Dataset":"CCTA119"}. This record does not assert independent reproduction.

### VSNet

DSC: 75.87. Result ID: 698b6ab57a967eddb76e64ff.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a0b1e209131cea80c50.md>)

Recorded evaluation configuration: {"Training Dataset":"CCTA119"}. This record does not assert independent reproduction.

### I2U-Net

DSC: 75.76. Result ID: 698b6ab57a967eddb76e64fd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a0b1e209131cea80c50.md>)

Recorded evaluation configuration: {"Training Dataset":"CCTA119"}. This record does not assert independent reproduction.

### nnFormer

DSC: 75.62. Result ID: 698b6ab57a967eddb76e64fe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a0b1e209131cea80c50.md>)

Recorded evaluation configuration: {"Training Dataset":"CCTA119"}. This record does not assert independent reproduction.

### 3D-UNet

DSC: 73.55. Result ID: 698b6ab57a967eddb76e64fc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a0b1e209131cea80c50.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa629d1e209131ce9fa34e.md>)

[Implementation](<http://lmb.informatik.uni-freiburg.de/resources/opensource/unet.en.html>)

Recorded evaluation configuration: {"Training Dataset":"CCTA119"}. This record does not assert independent reproduction.

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