# Skin Lesion Segmentation on ISBI 2017

Source: [Skin Lesion Segmentation on ISBI 2017](<https://www.sota2.com/research/sota/skin-lesion-segmentation-on-isbi-2017>)

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

Data updated: 2026-02-26T05:47:37.413Z

Evaluation of skin lesion segmentation performance on the ISBI 2017 dataset, reporting metrics including Jaccard Similarity Index (JSI), Accuracy (AC), and Dice Coefficient (DC).

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) | ISBI 2017 |
| Metric | JSI |
| 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

- [JSI](<https://www.sota2.com/research/sota/skin-lesion-segmentation-on-isbi-2017.md?metric=JSI>): Higher is better; unit: PERCENT.

- [Acc](<https://www.sota2.com/research/sota/skin-lesion-segmentation-on-isbi-2017.md?metric=Acc>): Higher is better; unit: PERCENT.

- [DC](<https://www.sota2.com/research/sota/skin-lesion-segmentation-on-isbi-2017.md?metric=DC>): Higher is better; unit: PERCENT.

## Recorded results

| Method | JSI | Result date | Report paper |
| --- | --- | --- | --- |
| Residual Multi-scale dual attention Unet | 83.83 | Not recorded | 68fa6cb31e209131cea3559b |
| \[32\] | 76.2 | Not recorded | 68fa6cb31e209131cea3559b |
| Automatic skin lesion analysis using large-scale dermoscopy images and deep residual networks | 76 | Not recorded | 68fa6cb31e209131cea3559b |
| \[50\] | 75.6 | Not recorded | 68fa6cb31e209131cea3559b |

### Residual Multi-scale dual attention Unet

JSI: 83.83. Result ID: 698f2fe73a6c314849f6cf08.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb31e209131cea3559b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cb31e209131cea3559b.md>)

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

### \[32\]

JSI: 76.2. Result ID: 698f2fe73a6c314849f6cf06.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb31e209131cea3559b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63cf1e209131cea00d19.md>)

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

### Automatic skin lesion analysis using large-scale dermoscopy images and deep residual networks

JSI: 76. Result ID: 698f2fe73a6c314849f6cf07.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb31e209131cea3559b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63311e209131ce9fd3bb.md>)

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

### \[50\]

JSI: 75.6. Result ID: 698f2fe73a6c314849f6cf05.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cb31e209131cea3559b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64261e209131cea02e8f.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.
