# Nuclei Detection and Classification on PUMA Challenge Track 2 (test)

Source: [Nuclei Detection and Classification on PUMA Challenge Track 2 (test)](<https://www.sota2.com/research/sota/nuclei-detection-and-classification-on-puma-challenge-track-2-test>)

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

Data updated: 2026-05-13T10:34:31.245Z

Evaluation of Nuclei Detection and Classification performance on the PUMA Challenge Track 2 test set, reporting F1 scores for multiple specific cell types including Tumour, Stroma, and Lymphocyte.

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 Detection and Classification |
| Dataset (including any stated split) | PUMA Challenge Track 2 (test) |
| Metric | Average F1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 10 of 10 |
| 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

- [Average F1](<https://www.sota2.com/research/sota/nuclei-detection-and-classification-on-puma-challenge-track-2-test.md?metric=Average%20F1>): Higher is better; unit: PERCENT.

- [Tumour F1](<https://www.sota2.com/research/sota/nuclei-detection-and-classification-on-puma-challenge-track-2-test.md?metric=Tumour%20F1>): Higher is better; unit: PERCENT.

- [Stroma F1](<https://www.sota2.com/research/sota/nuclei-detection-and-classification-on-puma-challenge-track-2-test.md?metric=Stroma%20F1>): Higher is better; unit: PERCENT.

- [Apoptosis F1](<https://www.sota2.com/research/sota/nuclei-detection-and-classification-on-puma-challenge-track-2-test.md?metric=Apoptosis%20F1>): Higher is better; unit: PERCENT.

- [Epithelium F1](<https://www.sota2.com/research/sota/nuclei-detection-and-classification-on-puma-challenge-track-2-test.md?metric=Epithelium%20F1>): Higher is better; unit: PERCENT.

- [Histiocyte F1](<https://www.sota2.com/research/sota/nuclei-detection-and-classification-on-puma-challenge-track-2-test.md?metric=Histiocyte%20F1>): Higher is better; unit: PERCENT.

- [Lymphocyte F1](<https://www.sota2.com/research/sota/nuclei-detection-and-classification-on-puma-challenge-track-2-test.md?metric=Lymphocyte%20F1>): Higher is better; unit: PERCENT.

- [Neutrophil F1](<https://www.sota2.com/research/sota/nuclei-detection-and-classification-on-puma-challenge-track-2-test.md?metric=Neutrophil%20F1>): Higher is better; unit: PERCENT.

- [Endothelium F1](<https://www.sota2.com/research/sota/nuclei-detection-and-classification-on-puma-challenge-track-2-test.md?metric=Endothelium%20F1>): Higher is better; unit: PERCENT.

- [Melanophage F1](<https://www.sota2.com/research/sota/nuclei-detection-and-classification-on-puma-challenge-track-2-test.md?metric=Melanophage%20F1>): Higher is better; unit: PERCENT.

- [Plasma F1](<https://www.sota2.com/research/sota/nuclei-detection-and-classification-on-puma-challenge-track-2-test.md?metric=Plasma%20F1>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Average F1 | Result date | Report paper |
| --- | --- | --- | --- |
| KongNet | 28.04 | Not recorded | 69004e153ef7ccd74e5e2eb3 |
| Team LSM | 27.6 | Not recorded | 69004e153ef7ccd74e5e2eb3 |
| Team LSM | 27.07 | Not recorded | 69004e153ef7ccd74e5e2eb3 |
| KongNet | 26.56 | Not recorded | 69004e153ef7ccd74e5e2eb3 |
| Team rictoo | 25.12 | Not recorded | 69004e153ef7ccd74e5e2eb3 |
| Team rictoo | 24.16 | Not recorded | 69004e153ef7ccd74e5e2eb3 |
| Team UME | 23.35 | Not recorded | 69004e153ef7ccd74e5e2eb3 |
| Baseline | 22.74 | Not recorded | 69004e153ef7ccd74e5e2eb3 |
| Team UME | 22.61 | Not recorded | 69004e153ef7ccd74e5e2eb3 |
| Baseline | 20.4 | Not recorded | 69004e153ef7ccd74e5e2eb3 |

### KongNet

Average F1: 28.04. Result ID: 6a04520747f34ce924ead87b.

[Reporting paper](<https://www.sota2.com/research/paper/69004e153ef7ccd74e5e2eb3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69004e153ef7ccd74e5e2eb3.md>)

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

### Team LSM

Average F1: 27.6. Result ID: 6a04520747f34ce924ead87c.

[Reporting paper](<https://www.sota2.com/research/paper/69004e153ef7ccd74e5e2eb3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea8602d.md>)

Recorded evaluation configuration: {"Model Description":"Multi-Stage Network"}. This record does not assert independent reproduction.

### Team LSM

Average F1: 27.07. Result ID: 6a04520747f34ce924ead859.

[Reporting paper](<https://www.sota2.com/research/paper/69004e153ef7ccd74e5e2eb3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea8602d.md>)

Recorded evaluation configuration: {"Model Architecture":"Multi-Stage Network"}. This record does not assert independent reproduction.

### KongNet

Average F1: 26.56. Result ID: 6a04520747f34ce924ead85a.

[Reporting paper](<https://www.sota2.com/research/paper/69004e153ef7ccd74e5e2eb3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69004e153ef7ccd74e5e2eb3.md>)

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

### Team rictoo

Average F1: 25.12. Result ID: 6a04520747f34ce924ead87d.

[Reporting paper](<https://www.sota2.com/research/paper/69004e153ef7ccd74e5e2eb3.md>)

Recorded evaluation configuration: {"status":"not publicly released"}. This record does not assert independent reproduction.

### Team rictoo

Average F1: 24.16. Result ID: 6a04520747f34ce924ead85b.

[Reporting paper](<https://www.sota2.com/research/paper/69004e153ef7ccd74e5e2eb3.md>)

Recorded evaluation configuration: {"Method Release Status":"not publicly released"}. This record does not assert independent reproduction.

### Team UME

Average F1: 23.35. Result ID: 6a04520747f34ce924ead85c.

[Reporting paper](<https://www.sota2.com/research/paper/69004e153ef7ccd74e5e2eb3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77731e209131cea7330f.md>)

Recorded evaluation configuration: {"Model Architecture":"CellViT++","Fine-tuning":"true","Hyperparameter Sweep":"true"}. This record does not assert independent reproduction.

### Baseline

Average F1: 22.74. Result ID: 6a04520747f34ce924ead87e.

[Reporting paper](<https://www.sota2.com/research/paper/69004e153ef7ccd74e5e2eb3.md>)

Recorded evaluation configuration: {"Backbone":"HoVer-NeXt"}. This record does not assert independent reproduction.

### Team UME

Average F1: 22.61. Result ID: 6a04520747f34ce924ead87f.

[Reporting paper](<https://www.sota2.com/research/paper/69004e153ef7ccd74e5e2eb3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77731e209131cea7330f.md>)

Recorded evaluation configuration: {"Backbone":"CellViT++","Fine-tuned":"true"}. This record does not assert independent reproduction.

### Baseline

Average F1: 20.4. Result ID: 6a04520747f34ce924ead85d.

[Reporting paper](<https://www.sota2.com/research/paper/69004e153ef7ccd74e5e2eb3.md>)

Recorded evaluation configuration: {"Model Architecture":"HoVer-NeXt"}. This record does not assert independent reproduction.

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