Cross-Validation Dice Scores for Model Evaluation

5.5 KB of results from a 5-fold cross-validation procedure, showing the best validation Dice score per fold. The data, published by Muthulakshmi Kirubakaran on figshare, was last updated on May 18, 2026. It is stored in an XLS file format.

Use Cases

• Compare model performance stability across different data folds based on reported validation scores.
• Benchmark segmentation algorithms using the aggregated mean and standard deviation of Dice scores.
• Analyze the variance in model generalization as suggested by the cross-validation results.

Strengths

• Data is licensed under CC-BY-4.0, permitting broad reuse.
• The 5-fold cross-validation method provides a standard measure of model performance.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Description metadata is limited; actual data quality requires manual inspection after download.

Provenance

Source

figshare

Collection Method

Likely generated from a machine learning model evaluation pipeline.

Freshness

Last updated 2026-05-18 17:47:21; freshness should be verified.