# Histopathology Classification on TCGA (test)

Source: [Histopathology Classification on TCGA (test)](<https://www.sota2.com/research/sota/histopathology-classification-on-tcga-test>)

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

Data updated: 2026-02-26T05:42:50.450Z

Evaluation of Histopathology Classification performance on the test split of the TCGA dataset, reporting detailed F1 scores across prognosis categories (Good, Intermediate, Poor) and Nontumor classes.

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 | Histopathology Classification |
| Dataset (including any stated split) | TCGA (test) |
| Metric | F1 (Good prognosis) |
| Unit | SCALAR |
| 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

- [F1 (Good prognosis)](<https://www.sota2.com/research/sota/histopathology-classification-on-tcga-test.md?metric=F1%20(Good%20prognosis)>): Higher is better; unit: SCALAR.

- [F1 (Intermediate prognosis)](<https://www.sota2.com/research/sota/histopathology-classification-on-tcga-test.md?metric=F1%20(Intermediate%20prognosis)>): Higher is better; unit: SCALAR.

- [F1 (Poor prognosis)](<https://www.sota2.com/research/sota/histopathology-classification-on-tcga-test.md?metric=F1%20(Poor%20prognosis)>): Higher is better; unit: SCALAR.

- [F1 (Nontumor)](<https://www.sota2.com/research/sota/histopathology-classification-on-tcga-test.md?metric=F1%20(Nontumor)>): Higher is better; unit: SCALAR.

- [Weighted F1](<https://www.sota2.com/research/sota/histopathology-classification-on-tcga-test.md?metric=Weighted%20F1>): Higher is better; unit: SCALAR.

- [Macro F1](<https://www.sota2.com/research/sota/histopathology-classification-on-tcga-test.md?metric=Macro%20F1>): Higher is better; unit: SCALAR.

## Recorded results

| Method | F1 (Good prognosis) | Result date | Report paper |
| --- | --- | --- | --- |
| LDM synthetic augmentation | 0.769 | Not recorded | 697846b3a2b28e761d87c613 |
| Macenko stain augmentation | 0.76 | Not recorded | 697846b3a2b28e761d87c613 |
| Standard augmentation | 0.756 | Not recorded | 697846b3a2b28e761d87c613 |
| No augmentation | 0.754 | Not recorded | 697846b3a2b28e761d87c613 |
| Color jittering | 0.753 | Not recorded | 697846b3a2b28e761d87c613 |
| LDM synthetic + Vahadane stain augmentation | 0.731 | Not recorded | 697846b3a2b28e761d87c613 |
| Geometric transformation | 0.73 | Not recorded | 697846b3a2b28e761d87c613 |
| Vahadane stain augmentation | 0.726 | Not recorded | 697846b3a2b28e761d87c613 |
| LDM synthetic + Macenko stain augmentation | 0.722 | Not recorded | 697846b3a2b28e761d87c613 |
| UNI + logistic regression | 0.597 | Not recorded | 697846b3a2b28e761d87c613 |

### LDM synthetic augmentation

F1 (Good prognosis): 0.769. Result ID: 699793755698665ec4e8f403.

[Reporting paper](<https://www.sota2.com/research/paper/697846b3a2b28e761d87c613.md>)

[Method origin paper](<https://www.sota2.com/research/paper/697846b3a2b28e761d87c613.md>)

Recorded evaluation configuration: {"Augmentation Strategy":"LDM synthetic"}. This record does not assert independent reproduction.

### Macenko stain augmentation

F1 (Good prognosis): 0.76. Result ID: 699793755698665ec4e8f401.

[Reporting paper](<https://www.sota2.com/research/paper/697846b3a2b28e761d87c613.md>)

Recorded evaluation configuration: {"Augmentation Strategy":"Macenko stain normalization"}. This record does not assert independent reproduction.

### Standard augmentation

F1 (Good prognosis): 0.756. Result ID: 699793755698665ec4e8f400.

[Reporting paper](<https://www.sota2.com/research/paper/697846b3a2b28e761d87c613.md>)

Recorded evaluation configuration: {"Augmentation Strategy":"Standard"}. This record does not assert independent reproduction.

### No augmentation

F1 (Good prognosis): 0.754. Result ID: 699793755698665ec4e8f3fd.

[Reporting paper](<https://www.sota2.com/research/paper/697846b3a2b28e761d87c613.md>)

Recorded evaluation configuration: {"Augmentation Strategy":"None"}. This record does not assert independent reproduction.

### Color jittering

F1 (Good prognosis): 0.753. Result ID: 699793755698665ec4e8f3ff.

[Reporting paper](<https://www.sota2.com/research/paper/697846b3a2b28e761d87c613.md>)

Recorded evaluation configuration: {"Augmentation Strategy":"Color jittering"}. This record does not assert independent reproduction.

### LDM synthetic + Vahadane stain augmentation

F1 (Good prognosis): 0.731. Result ID: 699793755698665ec4e8f405.

[Reporting paper](<https://www.sota2.com/research/paper/697846b3a2b28e761d87c613.md>)

[Method origin paper](<https://www.sota2.com/research/paper/697846b3a2b28e761d87c613.md>)

Recorded evaluation configuration: {"Augmentation Strategy":"LDM synthetic + Vahadane"}. This record does not assert independent reproduction.

### Geometric transformation

F1 (Good prognosis): 0.73. Result ID: 699793755698665ec4e8f3fe.

[Reporting paper](<https://www.sota2.com/research/paper/697846b3a2b28e761d87c613.md>)

Recorded evaluation configuration: {"Augmentation Strategy":"Geometric transformation"}. This record does not assert independent reproduction.

### Vahadane stain augmentation

F1 (Good prognosis): 0.726. Result ID: 699793755698665ec4e8f402.

[Reporting paper](<https://www.sota2.com/research/paper/697846b3a2b28e761d87c613.md>)

Recorded evaluation configuration: {"Augmentation Strategy":"Vahadane stain normalization"}. This record does not assert independent reproduction.

### LDM synthetic + Macenko stain augmentation

F1 (Good prognosis): 0.722. Result ID: 699793755698665ec4e8f404.

[Reporting paper](<https://www.sota2.com/research/paper/697846b3a2b28e761d87c613.md>)

[Method origin paper](<https://www.sota2.com/research/paper/697846b3a2b28e761d87c613.md>)

Recorded evaluation configuration: {"Augmentation Strategy":"LDM synthetic + Macenko"}. This record does not assert independent reproduction.

### UNI + logistic regression

F1 (Good prognosis): 0.597. Result ID: 699793755698665ec4e8f3fc.

[Reporting paper](<https://www.sota2.com/research/paper/697846b3a2b28e761d87c613.md>)

Recorded evaluation configuration: {"Backbone":"UNI","Classifier":"logistic regression"}. This record does not assert independent reproduction.

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