# Skin Lesion Segmentation on ISIC Official 256 2018

Source: [Skin Lesion Segmentation on ISIC Official 256 2018](<https://www.sota2.com/research/sota/skin-lesion-segmentation-on-isic-official-256-2018>)

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

Data updated: 2026-06-05T09:32:31.845Z

Evaluation of skin lesion segmentation performance on the ISIC Official 256 2018 dataset configuration, reporting metrics including Dice, IoU, Accuracy, Sensitivity, Specificity, Precision, B-F1, HD95, and 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 | Skin Lesion Segmentation |
| Dataset (including any stated split) | ISIC Official 256 2018 |
| Metric | 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

- [Dice](<https://www.sota2.com/research/sota/skin-lesion-segmentation-on-isic-official-256-2018.md?metric=Dice>): Higher is better; unit: PERCENT.

- [IoU](<https://www.sota2.com/research/sota/skin-lesion-segmentation-on-isic-official-256-2018.md?metric=IoU>): Higher is better; unit: PERCENT.

- [Accuracy](<https://www.sota2.com/research/sota/skin-lesion-segmentation-on-isic-official-256-2018.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Sensitivity](<https://www.sota2.com/research/sota/skin-lesion-segmentation-on-isic-official-256-2018.md?metric=Sensitivity>): Higher is better; unit: PERCENT.

- [Specificity](<https://www.sota2.com/research/sota/skin-lesion-segmentation-on-isic-official-256-2018.md?metric=Specificity>): Higher is better; unit: PERCENT.

- [Precision](<https://www.sota2.com/research/sota/skin-lesion-segmentation-on-isic-official-256-2018.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Balanced F1 Score](<https://www.sota2.com/research/sota/skin-lesion-segmentation-on-isic-official-256-2018.md?metric=Balanced%20F1%20Score>): Higher is better; unit: PERCENT.

- [HD95](<https://www.sota2.com/research/sota/skin-lesion-segmentation-on-isic-official-256-2018.md?metric=HD95>): Lower is better; unit: SCALAR.

- [ASSD](<https://www.sota2.com/research/sota/skin-lesion-segmentation-on-isic-official-256-2018.md?metric=ASSD>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Dice | Result date | Report paper |
| --- | --- | --- | --- |
| MS-DKC-AttNextTopo-VCSF | 88.72 | Not recorded | 6a22587b86173ad9c1468a3a |
| AttNextTopo-Baseline | 88.18 | Not recorded | 6a22587b86173ad9c1468a3a |
| MS-DKC-AttNext-SBR | 87.85 | Not recorded | 6a22587b86173ad9c1468a3a |
| U-Net | 86.22 | Not recorded | 6a22587b86173ad9c1468a3a |
| GLAD-Net | 85.6 | Not recorded | 6a22587b86173ad9c1468a3a |
| U-Net-Transformer | 83.19 | Not recorded | 6a22587b86173ad9c1468a3a |
| Shallow U-Net | 79.25 | Not recorded | 6a22587b86173ad9c1468a3a |

### MS-DKC-AttNextTopo-VCSF

Dice: 88.72. Result ID: 6a2297adfbc373592c2110f3.

[Reporting paper](<https://www.sota2.com/research/paper/6a22587b86173ad9c1468a3a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a22587b86173ad9c1468a3a.md>)

Recorded evaluation configuration: {"NoAug":"true"}. This record does not assert independent reproduction.

### AttNextTopo-Baseline

Dice: 88.18. Result ID: 6a2297adfbc373592c2110f2.

[Reporting paper](<https://www.sota2.com/research/paper/6a22587b86173ad9c1468a3a.md>)

Recorded evaluation configuration: {"NoAug":"true"}. This record does not assert independent reproduction.

### MS-DKC-AttNext-SBR

Dice: 87.85. Result ID: 6a2297adfbc373592c2110f1.

[Reporting paper](<https://www.sota2.com/research/paper/6a22587b86173ad9c1468a3a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a22587b86173ad9c1468a3a.md>)

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

### U-Net

Dice: 86.22. Result ID: 6a2297adfbc373592c2110ee.

[Reporting paper](<https://www.sota2.com/research/paper/6a22587b86173ad9c1468a3a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa61e11e209131ce9f653d.md>)

[Implementation](<http://lmb.informatik.uni-freiburg.de/people/ronneber/u-net>)

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

### GLAD-Net

Dice: 85.6. Result ID: 6a2297adfbc373592c2110f0.

[Reporting paper](<https://www.sota2.com/research/paper/6a22587b86173ad9c1468a3a.md>)

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

### U-Net-Transformer

Dice: 83.19. Result ID: 6a2297adfbc373592c2110ef.

[Reporting paper](<https://www.sota2.com/research/paper/6a22587b86173ad9c1468a3a.md>)

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

### Shallow U-Net

Dice: 79.25. Result ID: 6a2297adfbc373592c2110ed.

[Reporting paper](<https://www.sota2.com/research/paper/6a22587b86173ad9c1468a3a.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.
