# Semantic Segmentation on MeniSeg (test)

Source: [Semantic Segmentation on MeniSeg (test)](<https://www.sota2.com/research/sota/semantic-segmentation-on-meniseg-test>)

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

Data updated: 2026-02-26T06:07:44.412Z

Evaluation of Semantic Segmentation performance on the test split of the MeniSeg dataset, reporting Dice coefficients and Hausdorff Distance 95th percentile (HD95) for Tumor and Edema regions, along with average metrics.

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 | Semantic Segmentation |
| Dataset (including any stated split) | MeniSeg (test) |
| Metric | Tumor Dice |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

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

- [Tumor HD95](<https://www.sota2.com/research/sota/semantic-segmentation-on-meniseg-test.md?metric=Tumor%20HD95>): Lower is better; unit: SCALAR.

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

- [Edema HD95](<https://www.sota2.com/research/sota/semantic-segmentation-on-meniseg-test.md?metric=Edema%20HD95>): Lower is better; unit: SCALAR.

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

- [Average HD95](<https://www.sota2.com/research/sota/semantic-segmentation-on-meniseg-test.md?metric=Average%20HD95>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Tumor Dice | Result date | Report paper |
| --- | --- | --- | --- |
| NestedFormer | 83.4 | Not recorded | 68fa6d561e209131cea3943a |
| MAML | 81.9 | Not recorded | 68fa6d561e209131cea3943a |
| UNETR | 81.8 | Not recorded | 68fa6d561e209131cea3943a |
| SegResNet | 81.3 | Not recorded | 68fa6d561e209131cea3943a |
| TransBTS | 80.9 | Not recorded | 68fa6d561e209131cea3943a |
| SwinUNet(2D) | 80.7 | Not recorded | 68fa6d561e209131cea3943a |
| 3D-UNet | 79.9 | Not recorded | 68fa6d561e209131cea3943a |

### NestedFormer

Tumor Dice: 83.4. Result ID: 698f87643a6c314849f9b50f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d561e209131cea3943a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d561e209131cea3943a.md>)

[Implementation](<https://github.com/920232796/NestedFormer>)

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

### MAML

Tumor Dice: 81.9. Result ID: 698f87643a6c314849f9b50b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d561e209131cea3943a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a5e1e209131cea27c67.md>)

[Implementation](<https://github.com/YaoZhang93/MAML>)

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

### UNETR

Tumor Dice: 81.8. Result ID: 698f87643a6c314849f9b50e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d561e209131cea3943a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6afc1e209131cea2b881.md>)

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

### SegResNet

Tumor Dice: 81.3. Result ID: 698f87643a6c314849f9b50a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d561e209131cea3943a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5edf1e209131ce9e5e7c.md>)

[Implementation](<https://www.cbica.upenn.edu/BraTS18/lboardValidation.html>)

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

### TransBTS

Tumor Dice: 80.9. Result ID: 698f87643a6c314849f9b50d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d561e209131cea3943a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a3b1e209131cea26d24.md>)

[Implementation](<https://github.com/Wenxuan-1119/TransBTS>)

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

### SwinUNet(2D)

Tumor Dice: 80.7. Result ID: 698f87643a6c314849f9b50c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d561e209131cea3943a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69f01e209131cea2517c.md>)

[Implementation](<https://github.com/HuCaoFighting/Swin-Unet>)

Recorded evaluation configuration: {"dimension":"2D"}. This record does not assert independent reproduction.

### 3D-UNet

Tumor Dice: 79.9. Result ID: 698f87643a6c314849f9b509.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6d561e209131cea3943a.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: Not recorded. This record does not assert independent reproduction.

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