# Cirrhosis Classification on D\_histo^{1+2} (N=155)

Source: [Cirrhosis Classification on D\_histo^{1+2} (N=155)](<https://www.sota2.com/research/sota/cirrhosis-classification-on-d_histo-1-plus-2-n-155>)

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

Data updated: 2026-02-26T05:24:36.071Z

Evaluation of Cirrhosis Classification performance using the specific subset D\_histo^{1+2} containing 155 samples, typically measured by AUC.

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 | Cirrhosis Classification |
| Dataset (including any stated split) | D\_histo^{1+2} (N=155) |
| Metric | AUC |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 15 of 15 |
| 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

- [AUC](<https://www.sota2.com/research/sota/cirrhosis-classification-on-d_histo-1-plus-2-n-155.md?metric=AUC>): Higher is better; unit: SCALAR.

## Recorded results

| Method | AUC | Result date | Report paper |
| --- | --- | --- | --- |
| Weakly-supervised positional contrastive learning | 0.84 | Not recorded | 68fa709e1e209131cea4c4c3 |
| depth-Aware | 0.8 | Not recorded | 68fa709e1e209131cea4c4c3 |
| Weakly-supervised positional contrastive learning | 0.79 | Not recorded | 68fa709e1e209131cea4c4c3 |
| SimCLR | 0.79 | Not recorded | 68fa709e1e209131cea4c4c3 |
| BYOL | 0.78 | Not recorded | 68fa709e1e209131cea4c4c3 |
| BYOL | 0.77 | Not recorded | 68fa709e1e209131cea4c4c3 |
| depth-Aware | 0.77 | Not recorded | 68fa709e1e209131cea4c4c3 |
| SimCLR | 0.76 | Not recorded | 68fa709e1e209131cea4c4c3 |
| SupCon | 0.76 | Not recorded | 68fa709e1e209131cea4c4c3 |
| None (random initialization) | 0.73 | Not recorded | 68fa709e1e209131cea4c4c3 |
| SupCon | 0.72 | Not recorded | 68fa709e1e209131cea4c4c3 |
| Supervised | 0.72 | Not recorded | 68fa709e1e209131cea4c4c3 |
| Supervised | 0.71 | Not recorded | 68fa709e1e209131cea4c4c3 |
| None (random initialization) | 0.68 | Not recorded | 68fa709e1e209131cea4c4c3 |
| ImageNet (frozen representations) | 0.66 | Not recorded | 68fa709e1e209131cea4c4c3 |

### Weakly-supervised positional contrastive learning

AUC: 0.84. Result ID: 699137e33a6c314849069062.

[Reporting paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c4c3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c4c3.md>)

[Implementation](<https://github.com/Guerbet-AI/wsp-contrastive>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Weak labels":true,"Depth pos.":true}. This record does not assert independent reproduction.

### depth-Aware

AUC: 0.8. Result ID: 699137e33a6c314849069061.

[Reporting paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c4c3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a261e209131cea265c6.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Weak labels":false,"Depth pos.":true}. This record does not assert independent reproduction.

### Weakly-supervised positional contrastive learning

AUC: 0.79. Result ID: 699137e33a6c31484906905a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c4c3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c4c3.md>)

[Implementation](<https://github.com/Guerbet-AI/wsp-contrastive>)

Recorded evaluation configuration: {"Backbone":"TinyNet","Weak labels":true,"Depth pos.":true}. This record does not assert independent reproduction.

### SimCLR

AUC: 0.79. Result ID: 699137e33a6c31484906905e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c4c3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67d71e209131cea18de5.md>)

[Implementation](<https://github.com/google-research/simclr>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Weak labels":false,"Depth pos.":false}. This record does not assert independent reproduction.

### BYOL

AUC: 0.78. Result ID: 699137e33a6c31484906905f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c4c3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa684a1e209131cea1b1e9.md>)

[Implementation](<https://github.com/deepmind/deepmind-research/tree/byol>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Weak labels":false,"Depth pos.":false}. This record does not assert independent reproduction.

### BYOL

AUC: 0.77. Result ID: 699137e33a6c314849069057.

[Reporting paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c4c3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa684a1e209131cea1b1e9.md>)

[Implementation](<https://github.com/deepmind/deepmind-research/tree/byol>)

Recorded evaluation configuration: {"Backbone":"TinyNet","Weak labels":false,"Depth pos.":false}. This record does not assert independent reproduction.

### depth-Aware

AUC: 0.77. Result ID: 699137e33a6c314849069059.

[Reporting paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c4c3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a261e209131cea265c6.md>)

Recorded evaluation configuration: {"Backbone":"TinyNet","Weak labels":false,"Depth pos.":true}. This record does not assert independent reproduction.

### SimCLR

AUC: 0.76. Result ID: 699137e33a6c314849069056.

[Reporting paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c4c3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67d71e209131cea18de5.md>)

[Implementation](<https://github.com/google-research/simclr>)

Recorded evaluation configuration: {"Backbone":"TinyNet","Weak labels":false,"Depth pos.":false}. This record does not assert independent reproduction.

### SupCon

AUC: 0.76. Result ID: 699137e33a6c314849069060.

[Reporting paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c4c3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa697f1e209131cea22756.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Weak labels":true,"Depth pos.":false}. This record does not assert independent reproduction.

### None (random initialization)

AUC: 0.73. Result ID: 699137e33a6c314849069055.

[Reporting paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c4c3.md>)

Recorded evaluation configuration: {"Backbone":"TinyNet","Weak labels":false,"Depth pos.":false}. This record does not assert independent reproduction.

### SupCon

AUC: 0.72. Result ID: 699137e33a6c314849069058.

[Reporting paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c4c3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa697f1e209131cea22756.md>)

Recorded evaluation configuration: {"Backbone":"TinyNet","Weak labels":true,"Depth pos.":false}. This record does not assert independent reproduction.

### Supervised

AUC: 0.72. Result ID: 699137e33a6c31484906905b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c4c3.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Weak labels":false,"Depth pos.":false}. This record does not assert independent reproduction.

### Supervised

AUC: 0.71. Result ID: 699137e33a6c314849069054.

[Reporting paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c4c3.md>)

Recorded evaluation configuration: {"Backbone":"TinyNet","Weak labels":false,"Depth pos.":false}. This record does not assert independent reproduction.

### None (random initialization)

AUC: 0.68. Result ID: 699137e33a6c31484906905c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c4c3.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Weak labels":false,"Depth pos.":false}. This record does not assert independent reproduction.

### ImageNet (frozen representations)

AUC: 0.66. Result ID: 699137e33a6c31484906905d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa709e1e209131cea4c4c3.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Weak labels":false,"Depth pos.":false}. This record does not assert independent reproduction.

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