# Cell-level Histopathological Image Classification on Cell-level Colorectal Cancer (test)

Source: [Cell-level Histopathological Image Classification on Cell-level Colorectal Cancer (test)](<https://www.sota2.com/research/sota/cell-level-histopathological-image-classification-on-cell-level-colorectal-cancer-test>)

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

Data updated: 2026-03-05T09:18:02.631Z

Evaluation of cell-level histopathological image classification performance on the test split of the Cell-level Colorectal Cancer dataset, reporting Accuracy, Macro precision, and Macro F1.

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-level Histopathological Image Classification |
| Dataset (including any stated split) | Cell-level Colorectal Cancer (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 14 of 14 |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/cell-level-histopathological-image-classification-on-cell-level-colorectal-cancer-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Macro Precision](<https://www.sota2.com/research/sota/cell-level-histopathological-image-classification-on-cell-level-colorectal-cancer-test.md?metric=Macro%20Precision>): Higher is better; unit: PERCENT.

- [Macro F1 Score](<https://www.sota2.com/research/sota/cell-level-histopathological-image-classification-on-cell-level-colorectal-cancer-test.md?metric=Macro%20F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| CustomViT | 92 | Not recorded | 69a90e192d603e6de3e40950 |
| UNI | 79 | Not recorded | 69a90e192d603e6de3e40950 |
| ConvNeXt | 65 | Not recorded | 69a90e192d603e6de3e40950 |
| EfficientNet | 64 | Not recorded | 69a90e192d603e6de3e40950 |
| ResNet-RS50 | 63 | Not recorded | 69a90e192d603e6de3e40950 |
| ResNet | 61 | Not recorded | 69a90e192d603e6de3e40950 |
| NIN | 60 | Not recorded | 69a90e192d603e6de3e40950 |
| CNN | 59 | Not recorded | 69a90e192d603e6de3e40950 |
| UNI | 55 | Not recorded | 69a90e192d603e6de3e40950 |
| SE-ResNet | 53 | Not recorded | 69a90e192d603e6de3e40950 |
| ResNet-RS50 | 51 | Not recorded | 69a90e192d603e6de3e40950 |
| MLP | 49 | Not recorded | 69a90e192d603e6de3e40950 |
| CTransPath | 24 | Not recorded | 69a90e192d603e6de3e40950 |
| CTransPath | 9 | Not recorded | 69a90e192d603e6de3e40950 |

### CustomViT

Accuracy: 92. Result ID: 69a94a206dbb7075b9530149.

[Reporting paper](<https://www.sota2.com/research/paper/69a90e192d603e6de3e40950.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a90e192d603e6de3e40950.md>)

Recorded evaluation configuration: {"Stage":"–","flag\_limit":"4096"}. This record does not assert independent reproduction.

### UNI

Accuracy: 79. Result ID: 69a94a206dbb7075b9530150.

[Reporting paper](<https://www.sota2.com/research/paper/69a90e192d603e6de3e40950.md>)

Recorded evaluation configuration: {"Stage":"FT\_last","flag\_limit":"4096"}. This record does not assert independent reproduction.

### ConvNeXt

Accuracy: 65. Result ID: 69a94a206dbb7075b953014a.

[Reporting paper](<https://www.sota2.com/research/paper/69a90e192d603e6de3e40950.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a90e192d603e6de3e40950.md>)

Recorded evaluation configuration: {"Stage":"–","flag\_limit":"4096"}. This record does not assert independent reproduction.

### EfficientNet

Accuracy: 64. Result ID: 69a94a206dbb7075b9530148.

[Reporting paper](<https://www.sota2.com/research/paper/69a90e192d603e6de3e40950.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a90e192d603e6de3e40950.md>)

Recorded evaluation configuration: {"Stage":"–","flag\_limit":"4096"}. This record does not assert independent reproduction.

### ResNet-RS50

Accuracy: 63. Result ID: 69a94a206dbb7075b953014c.

[Reporting paper](<https://www.sota2.com/research/paper/69a90e192d603e6de3e40950.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa697a1e209131cea224ee.md>)

[Implementation](<https://github.com/tensorflow/tpu/tree/master/models/official/resnet/resnet_rs>)

Recorded evaluation configuration: {"Stage":"FT\_last","flag\_limit":"4096"}. This record does not assert independent reproduction.

### ResNet

Accuracy: 61. Result ID: 69a94a206dbb7075b9530146.

[Reporting paper](<https://www.sota2.com/research/paper/69a90e192d603e6de3e40950.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a90e192d603e6de3e40950.md>)

Recorded evaluation configuration: {"Stage":"–","flag\_limit":"4096"}. This record does not assert independent reproduction.

### NIN

Accuracy: 60. Result ID: 69a94a206dbb7075b9530145.

[Reporting paper](<https://www.sota2.com/research/paper/69a90e192d603e6de3e40950.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a90e192d603e6de3e40950.md>)

Recorded evaluation configuration: {"Stage":"–","flag\_limit":"4096"}. This record does not assert independent reproduction.

### CNN

Accuracy: 59. Result ID: 69a94a206dbb7075b9530144.

[Reporting paper](<https://www.sota2.com/research/paper/69a90e192d603e6de3e40950.md>)

Recorded evaluation configuration: {"Stage":"–","flag\_limit":"4096"}. This record does not assert independent reproduction.

### UNI

Accuracy: 55. Result ID: 69a94a206dbb7075b953014f.

[Reporting paper](<https://www.sota2.com/research/paper/69a90e192d603e6de3e40950.md>)

Recorded evaluation configuration: {"Stage":"LP","flag\_limit":"4096"}. This record does not assert independent reproduction.

### SE-ResNet

Accuracy: 53. Result ID: 69a94a206dbb7075b9530147.

[Reporting paper](<https://www.sota2.com/research/paper/69a90e192d603e6de3e40950.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a90e192d603e6de3e40950.md>)

Recorded evaluation configuration: {"Stage":"–","flag\_limit":"4096"}. This record does not assert independent reproduction.

### ResNet-RS50

Accuracy: 51. Result ID: 69a94a206dbb7075b953014b.

[Reporting paper](<https://www.sota2.com/research/paper/69a90e192d603e6de3e40950.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa697a1e209131cea224ee.md>)

[Implementation](<https://github.com/tensorflow/tpu/tree/master/models/official/resnet/resnet_rs>)

Recorded evaluation configuration: {"Stage":"LP","flag\_limit":"4096"}. This record does not assert independent reproduction.

### MLP

Accuracy: 49. Result ID: 69a94a206dbb7075b9530143.

[Reporting paper](<https://www.sota2.com/research/paper/69a90e192d603e6de3e40950.md>)

Recorded evaluation configuration: {"Stage":"–","flag\_limit":"4096"}. This record does not assert independent reproduction.

### CTransPath

Accuracy: 24. Result ID: 69a94a206dbb7075b953014e.

[Reporting paper](<https://www.sota2.com/research/paper/69a90e192d603e6de3e40950.md>)

Recorded evaluation configuration: {"Stage":"FT\_last","flag\_limit":"4096"}. This record does not assert independent reproduction.

### CTransPath

Accuracy: 9. Result ID: 69a94a206dbb7075b953014d.

[Reporting paper](<https://www.sota2.com/research/paper/69a90e192d603e6de3e40950.md>)

Recorded evaluation configuration: {"Stage":"LP","flag\_limit":"4096"}. This record does not assert independent reproduction.

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