# Nuclei Segmentation on MoNuSeg transfer from PanNuke (test)

Source: [Nuclei Segmentation on MoNuSeg transfer from PanNuke (test)](<https://www.sota2.com/research/sota/nuclei-segmentation-on-monuseg-transfer-from-pannuke-test>)

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

Data updated: 2026-03-24T12:54:43.846Z

Evaluation of Nuclei Segmentation performance on the test split of the MoNuSeg dataset, specifically for models derived from a transfer learning setup originating from the PanNuke domain. Reports Dice and IoU scores.

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 | Nuclei Segmentation |
| Dataset (including any stated split) | MoNuSeg transfer from PanNuke (test) |
| Metric | Dice Score |
| 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 Score](<https://www.sota2.com/research/sota/nuclei-segmentation-on-monuseg-transfer-from-pannuke-test.md?metric=Dice%20Score>): Higher is better; unit: PERCENT.

- [mIoU](<https://www.sota2.com/research/sota/nuclei-segmentation-on-monuseg-transfer-from-pannuke-test.md?metric=mIoU>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Dice Score | Result date | Report paper |
| --- | --- | --- | --- |
| prompt-free lightweight SAM adaptation | 80.65 | Not recorded | 69c21a890636e5bf4afc4822 |
| SAM | 76.16 | Not recorded | 69c21a890636e5bf4afc4822 |
| SAM + LoRA | 76.02 | Not recorded | 69c21a890636e5bf4afc4822 |
| Swin-Unet | 74.2 | Not recorded | 69c21a890636e5bf4afc4822 |
| Trans-SAM | 56.31 | Not recorded | 69c21a890636e5bf4afc4822 |
| UNet | 51.43 | Not recorded | 69c21a890636e5bf4afc4822 |
| UCTransNet | 36.38 | Not recorded | 69c21a890636e5bf4afc4822 |

### prompt-free lightweight SAM adaptation

Dice Score: 80.65. Result ID: 69c288bd47f34ce924aa9a7d.

[Reporting paper](<https://www.sota2.com/research/paper/69c21a890636e5bf4afc4822.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c21a890636e5bf4afc4822.md>)

Recorded evaluation configuration: {"Source Training Dataset":"PanNuke","Evaluation Protocol":"Cross-dataset generalization"}. This record does not assert independent reproduction.

### SAM

Dice Score: 76.16. Result ID: 69c288bd47f34ce924aa9a7a.

[Reporting paper](<https://www.sota2.com/research/paper/69c21a890636e5bf4afc4822.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f0a1e209131cea437f2.md>)

[Implementation](<https://segment-anything.com/>)

Recorded evaluation configuration: {"Source Training Dataset":"PanNuke","Evaluation Protocol":"Cross-dataset generalization"}. This record does not assert independent reproduction.

### SAM + LoRA

Dice Score: 76.02. Result ID: 69c288bd47f34ce924aa9a7b.

[Reporting paper](<https://www.sota2.com/research/paper/69c21a890636e5bf4afc4822.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b121e209131cea2bf59.md>)

[Implementation](<https://github.com/microsoft/LoRA>)

Recorded evaluation configuration: {"Source Training Dataset":"PanNuke","Evaluation Protocol":"Cross-dataset generalization"}. This record does not assert independent reproduction.

### Swin-Unet

Dice Score: 74.2. Result ID: 69c288bd47f34ce924aa9a78.

[Reporting paper](<https://www.sota2.com/research/paper/69c21a890636e5bf4afc4822.md>)

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

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

Recorded evaluation configuration: {"Source Training Dataset":"PanNuke","Evaluation Protocol":"Cross-dataset generalization"}. This record does not assert independent reproduction.

### Trans-SAM

Dice Score: 56.31. Result ID: 69c288bd47f34ce924aa9a7c.

[Reporting paper](<https://www.sota2.com/research/paper/69c21a890636e5bf4afc4822.md>)

Recorded evaluation configuration: {"Source Training Dataset":"PanNuke","Evaluation Protocol":"Cross-dataset generalization"}. This record does not assert independent reproduction.

### UNet

Dice Score: 51.43. Result ID: 69c288bd47f34ce924aa9a77.

[Reporting paper](<https://www.sota2.com/research/paper/69c21a890636e5bf4afc4822.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: {"Source Training Dataset":"PanNuke","Evaluation Protocol":"Cross-dataset generalization"}. This record does not assert independent reproduction.

### UCTransNet

Dice Score: 36.38. Result ID: 69c288bd47f34ce924aa9a79.

[Reporting paper](<https://www.sota2.com/research/paper/69c21a890636e5bf4afc4822.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ba01e209131cea2f63c.md>)

[Implementation](<https://github.com/McGregorWwww/UCTransNet>)

Recorded evaluation configuration: {"Source Training Dataset":"PanNuke","Evaluation Protocol":"Cross-dataset generalization"}. This record does not assert independent reproduction.

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