# Microtubule segmentation on MicReal\_FluoMT (test)

Source: [Microtubule segmentation on MicReal\_FluoMT (test)](<https://www.sota2.com/research/sota/microtubule-segmentation-on-micreal_fluomt-test>)

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

Data updated: 2026-06-23T09:23:23.131Z

Evaluation of model performance for microtubule segmentation on the test split of the real MicReal\_FluoMT dataset, reporting a comprehensive set of segmentation quality and ranking metrics.

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 | Microtubule segmentation |
| Dataset (including any stated split) | MicReal\_FluoMT (test) |
| Metric | Dice Coefficient |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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 Coefficient](<https://www.sota2.com/research/sota/microtubule-segmentation-on-micreal_fluomt-test.md?metric=Dice%20Coefficient>): Higher is better; unit: PERCENT.

- [Intersection over Union (IoU)](<https://www.sota2.com/research/sota/microtubule-segmentation-on-micreal_fluomt-test.md?metric=Intersection%20over%20Union%20(IoU)>): Higher is better; unit: PERCENT.

- [Sensitivity (SE)](<https://www.sota2.com/research/sota/microtubule-segmentation-on-micreal_fluomt-test.md?metric=Sensitivity%20(SE)>): Higher is better; unit: PERCENT.

- [Precision (Prec.)](<https://www.sota2.com/research/sota/microtubule-segmentation-on-micreal_fluomt-test.md?metric=Precision%20(Prec.)>): Higher is better; unit: PERCENT.

- [Specificity (SP)](<https://www.sota2.com/research/sota/microtubule-segmentation-on-micreal_fluomt-test.md?metric=Specificity%20(SP)>): Higher is better; unit: PERCENT.

- [Accuracy (Acc.)](<https://www.sota2.com/research/sota/microtubule-segmentation-on-micreal_fluomt-test.md?metric=Accuracy%20(Acc.)>): Higher is better; unit: PERCENT.

- [Matthews Correlation Coefficient (MCC)](<https://www.sota2.com/research/sota/microtubule-segmentation-on-micreal_fluomt-test.md?metric=Matthews%20Correlation%20Coefficient%20(MCC)>): Higher is better; unit: SCALAR.

- [AUC-ROC](<https://www.sota2.com/research/sota/microtubule-segmentation-on-micreal_fluomt-test.md?metric=AUC-ROC>): Higher is better; unit: PERCENT.

- [AUC-PR](<https://www.sota2.com/research/sota/microtubule-segmentation-on-micreal_fluomt-test.md?metric=AUC-PR>): Higher is better; unit: PERCENT.

- [Class Dice (clDice)](<https://www.sota2.com/research/sota/microtubule-segmentation-on-micreal_fluomt-test.md?metric=Class%20Dice%20(clDice)>): Higher is better; unit: PERCENT.

- [Hausdorff Distance 95% (HD95)](<https://www.sota2.com/research/sota/microtubule-segmentation-on-micreal_fluomt-test.md?metric=Hausdorff%20Distance%2095%25%20(HD95)>): Lower is better; unit: OTHER.

## Recorded results

| Method | Dice Coefficient | Result date | Report paper |
| --- | --- | --- | --- |
| CurvSegFlow | 70.93 | Not recorded | 6a3a134e206542251d7c72a5 |
| nnU-Net 2021 | 70.4 | Not recorded | 6a3a134e206542251d7c72a5 |
| U-Net++ 2018 | 70.38 | Not recorded | 6a3a134e206542251d7c72a5 |
| U-Net 2015 | 66.17 | Not recorded | 6a3a134e206542251d7c72a5 |
| Synseg 2025 | 52.92 | Not recorded | 6a3a134e206542251d7c72a5 |

### CurvSegFlow

Dice Coefficient: 70.93. Result ID: 6a3a507bfbc373592c35b443.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a134e206542251d7c72a5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3a134e206542251d7c72a5.md>)

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

### nnU-Net 2021

Dice Coefficient: 70.4. Result ID: 6a3a507bfbc373592c35b441.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a134e206542251d7c72a5.md>)

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

### U-Net++ 2018

Dice Coefficient: 70.38. Result ID: 6a3a507bfbc373592c35b440.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a134e206542251d7c72a5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa649c1e209131cea058a9.md>)

[Implementation](<https://www.sota2.com/github.com/Nested-UNet>)

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

### U-Net 2015

Dice Coefficient: 66.17. Result ID: 6a3a507bfbc373592c35b43f.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a134e206542251d7c72a5.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.

### Synseg 2025

Dice Coefficient: 52.92. Result ID: 6a3a507bfbc373592c35b442.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a134e206542251d7c72a5.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.