# Liver fibrosis staging on Substantial Fibrosis S1 vs S2-4

Source: [Liver fibrosis staging on Substantial Fibrosis S1 vs S2-4](<https://www.sota2.com/research/sota/liver-fibrosis-staging-on-substantial-fibrosis-s1-vs-s2-4>)

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

Data updated: 2026-02-26T05:29:01.174Z

Evaluation of model performance for liver fibrosis staging using the Substantial Fibrosis S1 vs S2-4 dataset, reporting Accuracy, AUC, and ECE.

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 | Liver fibrosis staging |
| Dataset (including any stated split) | Substantial Fibrosis S1 vs S2-4 |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 12 of 12 |
| 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/liver-fibrosis-staging-on-substantial-fibrosis-s1-vs-s2-4.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [AUC](<https://www.sota2.com/research/sota/liver-fibrosis-staging-on-substantial-fibrosis-s1-vs-s2-4.md?metric=AUC>): Higher is better; unit: PERCENT.

- [ECE](<https://www.sota2.com/research/sota/liver-fibrosis-staging-on-substantial-fibrosis-s1-vs-s2-4.md?metric=ECE>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Reliable and Interpretable Multi-view Learning Framework | 85.5 | Not recorded | 68fa6fc81e209131cea475cc |
| Reliable and Interpretable Multi-view Learning Framework | 85.5 | Not recorded | 68fa6fc81e209131cea475cc |
| CMC | 83.4 | Not recorded | 68fa6fc81e209131cea475cc |
| DCCAE | 83.1 | Not recorded | 68fa6fc81e209131cea475cc |
| Attention | 81.4 | Not recorded | 68fa6fc81e209131cea475cc |
| VI | 81.1 | Not recorded | 68fa6fc81e209131cea475cc |
| PredSum | 81.1 | Not recorded | 68fa6fc81e209131cea475cc |
| Concat | 80.5 | Not recorded | 68fa6fc81e209131cea475cc |
| Dropout | 80.2 | Not recorded | 68fa6fc81e209131cea475cc |
| Ensemble | 79.3 | Not recorded | 68fa6fc81e209131cea475cc |
| Softmax | 78.2 | Not recorded | 68fa6fc81e209131cea475cc |
| SingleView | 78.2 | Not recorded | 68fa6fc81e209131cea475cc |

### Reliable and Interpretable Multi-view Learning Framework

Accuracy: 85.5. Result ID: 6990fe273a6c31484904dcb2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fc81e209131cea475cc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fc81e209131cea475cc.md>)

Recorded evaluation configuration: {"uncertainty\_estimation":"Uncertainty-aware fusion"}. This record does not assert independent reproduction.

### Reliable and Interpretable Multi-view Learning Framework

Accuracy: 85.5. Result ID: 6990fe273a6c31484904dcc0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fc81e209131cea475cc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fc81e209131cea475cc.md>)

Recorded evaluation configuration: {"fusion\_strategy":"uncertainty-aware"}. This record does not assert independent reproduction.

### CMC

Accuracy: 83.4. Result ID: 6990fe273a6c31484904dcbd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fc81e209131cea475cc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68f01e209131cea1f185.md>)

[Implementation](<http://github.com/HobbitLong/CMC/>)

Recorded evaluation configuration: {"fusion\_strategy":"feature level"}. This record does not assert independent reproduction.

### DCCAE

Accuracy: 83.1. Result ID: 6990fe273a6c31484904dcbc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fc81e209131cea475cc.md>)

Recorded evaluation configuration: {"fusion\_strategy":"feature level"}. This record does not assert independent reproduction.

### Attention

Accuracy: 81.4. Result ID: 6990fe273a6c31484904dcbf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fc81e209131cea475cc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64861e209131cea052eb.md>)

Recorded evaluation configuration: {"fusion\_strategy":"decision level"}. This record does not assert independent reproduction.

### VI

Accuracy: 81.1. Result ID: 6990fe273a6c31484904dcb0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fc81e209131cea475cc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66661e209131cea101fb.md>)

Recorded evaluation configuration: {"uncertainty\_estimation":"Variational Inference"}. This record does not assert independent reproduction.

### PredSum

Accuracy: 81.1. Result ID: 6990fe273a6c31484904dcbe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fc81e209131cea475cc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa61951e209131ce9f4ccf.md>)

Recorded evaluation configuration: {"fusion\_strategy":"decision level"}. This record does not assert independent reproduction.

### Concat

Accuracy: 80.5. Result ID: 6990fe273a6c31484904dcbb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fc81e209131cea475cc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62bc1e209131ce9faf52.md>)

[Implementation](<https://github.com/feichtenhofer/twostreamfusion>)

Recorded evaluation configuration: {"fusion\_strategy":"input level"}. This record does not assert independent reproduction.

### Dropout

Accuracy: 80.2. Result ID: 6990fe273a6c31484904dcaf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fc81e209131cea475cc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67241e209131cea14a89.md>)

Recorded evaluation configuration: {"uncertainty\_estimation":"Monte-Carlo Dropout"}. This record does not assert independent reproduction.

### Ensemble

Accuracy: 79.3. Result ID: 6990fe273a6c31484904dcb1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fc81e209131cea475cc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a391e209131cea26c08.md>)

Recorded evaluation configuration: {"uncertainty\_estimation":"Deep Ensemble"}. This record does not assert independent reproduction.

### Softmax

Accuracy: 78.2. Result ID: 6990fe273a6c31484904dcae.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fc81e209131cea475cc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a1d1e209131cea26052.md>)

Recorded evaluation configuration: {"uncertainty\_estimation":"Softmax Entropy"}. This record does not assert independent reproduction.

### SingleView

Accuracy: 78.2. Result ID: 6990fe273a6c31484904dcba.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fc81e209131cea475cc.md>)

Recorded evaluation configuration: {"input\_type":"single patch"}. This record does not assert independent reproduction.

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