# Cell Instance Segmentation on DSB 10% 2018 (test)

Source: [Cell Instance Segmentation on DSB 10% 2018 (test)](<https://www.sota2.com/research/sota/cell-instance-segmentation-on-dsb-10-percent-2018-test>)

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

Data updated: 2026-02-26T06:09:24.758Z

Evaluation of cell instance segmentation performance on the 10% test subset of the Data Science Bowl (DSB) 2018 dataset, reporting Average Precision metrics across various IoU thresholds.

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 | Cell Instance Segmentation |
| Dataset (including any stated split) | DSB 10% 2018 (test) |
| Metric | mAP |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

- [mAP](<https://www.sota2.com/research/sota/cell-instance-segmentation-on-dsb-10-percent-2018-test.md?metric=mAP>): Higher is better; unit: PERCENT.

- [AP @ IoU=0.50](<https://www.sota2.com/research/sota/cell-instance-segmentation-on-dsb-10-percent-2018-test.md?metric=AP%20%40%20IoU%3D0.50>): Higher is better; unit: PERCENT.

- [AP @ IoU=0.55](<https://www.sota2.com/research/sota/cell-instance-segmentation-on-dsb-10-percent-2018-test.md?metric=AP%20%40%20IoU%3D0.55>): Higher is better; unit: PERCENT.

- [AP @ IoU=0.60](<https://www.sota2.com/research/sota/cell-instance-segmentation-on-dsb-10-percent-2018-test.md?metric=AP%20%40%20IoU%3D0.60>): Higher is better; unit: PERCENT.

- [AP @ IoU=0.65](<https://www.sota2.com/research/sota/cell-instance-segmentation-on-dsb-10-percent-2018-test.md?metric=AP%20%40%20IoU%3D0.65>): Higher is better; unit: PERCENT.

- [AP @ IoU=0.70](<https://www.sota2.com/research/sota/cell-instance-segmentation-on-dsb-10-percent-2018-test.md?metric=AP%20%40%20IoU%3D0.70>): Higher is better; unit: PERCENT.

- [AP @ IoU=0.75](<https://www.sota2.com/research/sota/cell-instance-segmentation-on-dsb-10-percent-2018-test.md?metric=AP%20%40%20IoU%3D0.75>): Higher is better; unit: PERCENT.

- [AP @ IoU=0.80](<https://www.sota2.com/research/sota/cell-instance-segmentation-on-dsb-10-percent-2018-test.md?metric=AP%20%40%20IoU%3D0.80>): Higher is better; unit: PERCENT.

- [AP @ IoU=0.85](<https://www.sota2.com/research/sota/cell-instance-segmentation-on-dsb-10-percent-2018-test.md?metric=AP%20%40%20IoU%3D0.85>): Higher is better; unit: PERCENT.

- [AP @ IoU=0.90](<https://www.sota2.com/research/sota/cell-instance-segmentation-on-dsb-10-percent-2018-test.md?metric=AP%20%40%20IoU%3D0.90>): Higher is better; unit: PERCENT.

## Recorded results

| Method | mAP | Result date | Report paper |
| --- | --- | --- | --- |
| PolarMask++ | 74.2 | Not recorded | 68fa69eb1e209131cea24eb2 |
| Nuclei R-CNN | 69.6 | Not recorded | 68fa69eb1e209131cea24eb2 |
| PatchPerPix | 68.1 | Not recorded | 68fa69eb1e209131cea24eb2 |
| Li et al | 61.1 | Not recorded | 68fa69eb1e209131cea24eb2 |
| Mask R-CNN | 60.5 | Not recorded | 68fa69eb1e209131cea24eb2 |
| U-Net | 59.8 | Not recorded | 68fa69eb1e209131cea24eb2 |
| StarDist | 59.8 | Not recorded | 68fa69eb1e209131cea24eb2 |
| DCAN | 51.1 | Not recorded | 68fa69eb1e209131cea24eb2 |

### PolarMask++

mAP: 74.2. Result ID: 698df434ffc3901de099bdbb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69eb1e209131cea24eb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69eb1e209131cea24eb2.md>)

[Implementation](<https://www.sota2.com/github.com/xieenze/PolarMask>)

Recorded evaluation configuration: {"representation":"polar","single-scale":"true","backbone":"ResNet-50"}. This record does not assert independent reproduction.

### Nuclei R-CNN

mAP: 69.6. Result ID: 698df434ffc3901de099bdb8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69eb1e209131cea24eb2.md>)

Recorded evaluation configuration: {"representation":"pixel","single-scale":"true"}. This record does not assert independent reproduction.

### PatchPerPix

mAP: 68.1. Result ID: 698df434ffc3901de099bdba.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69eb1e209131cea24eb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e2c1e209131cea3e52b.md>)

Recorded evaluation configuration: {"representation":"pixel","single-scale":"true"}. This record does not assert independent reproduction.

### Li et al

mAP: 61.1. Result ID: 698df434ffc3901de099bdb9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69eb1e209131cea24eb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66ad1e209131cea11a7c.md>)

Recorded evaluation configuration: {"representation":"pixel","single-scale":"true"}. This record does not assert independent reproduction.

### Mask R-CNN

mAP: 60.5. Result ID: 698df434ffc3901de099bdb5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69eb1e209131cea24eb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63f21e209131cea01b22.md>)

[Implementation](<https://github.com/facebookresearch/Detectron>)

Recorded evaluation configuration: {"representation":"pixel","single-scale":"true"}. This record does not assert independent reproduction.

### U-Net

mAP: 59.8. Result ID: 698df434ffc3901de099bdb4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69eb1e209131cea24eb2.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: {"representation":"pixel","single-scale":"true"}. This record does not assert independent reproduction.

### StarDist

mAP: 59.8. Result ID: 698df434ffc3901de099bdb6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69eb1e209131cea24eb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65001e209131cea07bd4.md>)

[Implementation](<https://github.com/mpicbg-csbd/stardist>)

Recorded evaluation configuration: {"representation":"polar","single-scale":"true"}. This record does not assert independent reproduction.

### DCAN

mAP: 51.1. Result ID: 698df434ffc3901de099bdb3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa69eb1e209131cea24eb2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62681e209131ce9f92f8.md>)

Recorded evaluation configuration: {"representation":"pixel","single-scale":"true"}. This record does not assert independent reproduction.

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