# Developmental Stage Classification on Human embryo dataset (test)

Source: [Developmental Stage Classification on Human embryo dataset (test)](<https://www.sota2.com/research/sota/developmental-stage-classification-on-human-embryo-dataset-test>)

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

Data updated: 2026-02-26T05:45:59.508Z

Evaluation of Developmental Stage Classification performance on the test split of the Human embryo dataset, reporting various accuracy metrics across different developmental stages.

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 | Developmental Stage Classification |
| Dataset (including any stated split) | Human embryo dataset (test) |
| Metric | Global Accuracy |
| 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

- [Global Accuracy](<https://www.sota2.com/research/sota/developmental-stage-classification-on-human-embryo-dataset-test.md?metric=Global%20Accuracy>): Higher is better; unit: PERCENT.

- [Per-Stage Accuracy](<https://www.sota2.com/research/sota/developmental-stage-classification-on-human-embryo-dataset-test.md?metric=Per-Stage%20Accuracy>): Higher is better; unit: PERCENT.

- [Stage 1 Accuracy](<https://www.sota2.com/research/sota/developmental-stage-classification-on-human-embryo-dataset-test.md?metric=Stage%201%20Accuracy>): Higher is better; unit: PERCENT.

- [Stage 2 Accuracy](<https://www.sota2.com/research/sota/developmental-stage-classification-on-human-embryo-dataset-test.md?metric=Stage%202%20Accuracy>): Higher is better; unit: PERCENT.

- [Stage 3 Accuracy](<https://www.sota2.com/research/sota/developmental-stage-classification-on-human-embryo-dataset-test.md?metric=Stage%203%20Accuracy>): Higher is better; unit: PERCENT.

- [Stage 4 Accuracy](<https://www.sota2.com/research/sota/developmental-stage-classification-on-human-embryo-dataset-test.md?metric=Stage%204%20Accuracy>): Higher is better; unit: PERCENT.

- [Stage 5 Accuracy](<https://www.sota2.com/research/sota/developmental-stage-classification-on-human-embryo-dataset-test.md?metric=Stage%205%20Accuracy>): Higher is better; unit: PERCENT.

- [Stage 6 Accuracy](<https://www.sota2.com/research/sota/developmental-stage-classification-on-human-embryo-dataset-test.md?metric=Stage%206%20Accuracy>): Higher is better; unit: PERCENT.

- [Stage 7 Accuracy](<https://www.sota2.com/research/sota/developmental-stage-classification-on-human-embryo-dataset-test.md?metric=Stage%207%20Accuracy>): Higher is better; unit: PERCENT.

- [Stage 8 Accuracy](<https://www.sota2.com/research/sota/developmental-stage-classification-on-human-embryo-dataset-test.md?metric=Stage%208%20Accuracy>): Higher is better; unit: PERCENT.

- [Stage 9+ Accuracy](<https://www.sota2.com/research/sota/developmental-stage-classification-on-human-embryo-dataset-test.md?metric=Stage%209%2B%20Accuracy>): Higher is better; unit: PERCENT.

- [Stage M Accuracy](<https://www.sota2.com/research/sota/developmental-stage-classification-on-human-embryo-dataset-test.md?metric=Stage%20M%20Accuracy>): Higher is better; unit: PERCENT.

- [Stage B Accuracy](<https://www.sota2.com/research/sota/developmental-stage-classification-on-human-embryo-dataset-test.md?metric=Stage%20B%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Global Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Two-Stream Linear-Chain CRF | 80.6 | Not recorded | 68fa6a611e209131cea27e09 |
| AutoIVF | 77.8 | Not recorded | 68fa6a611e209131cea27e09 |
| LSTM | 77.1 | Not recorded | 68fa6a611e209131cea27e09 |
| Early Fusion | 75.1 | Not recorded | 68fa6a611e209131cea27e09 |
| ResNet50 | 74.6 | Not recorded | 68fa6a611e209131cea27e09 |

### Two-Stream Linear-Chain CRF

Global Accuracy: 80.6. Result ID: 698e30f7ffc3901de09b8836.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a611e209131cea27e09.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a611e209131cea27e09.md>)

Recorded evaluation configuration: {"Classification Model Category":"Spatiotemporal Classification Model"}. This record does not assert independent reproduction.

### AutoIVF

Global Accuracy: 77.8. Result ID: 698e30f7ffc3901de09b8833.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a611e209131cea27e09.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5eff1e209131ce9e6c92.md>)

Recorded evaluation configuration: {"Classification Model Category":"Per-Image Classification Model"}. This record does not assert independent reproduction.

### LSTM

Global Accuracy: 77.1. Result ID: 698e30f7ffc3901de09b8835.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a611e209131cea27e09.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65a31e209131cea0b78a.md>)

Recorded evaluation configuration: {"Classification Model Category":"Spatiotemporal Classification Model"}. This record does not assert independent reproduction.

### Early Fusion

Global Accuracy: 75.1. Result ID: 698e30f7ffc3901de09b8834.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a611e209131cea27e09.md>)

Recorded evaluation configuration: {"Classification Model Category":"Spatiotemporal Classification Model"}. This record does not assert independent reproduction.

### ResNet50

Global Accuracy: 74.6. Result ID: 698e30f7ffc3901de09b8832.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a611e209131cea27e09.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62321e209131ce9f8328.md>)

Recorded evaluation configuration: {"Classification Model Category":"Per-Image Classification Model"}. This record does not assert independent reproduction.

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