Dataset Splits for Disease Severity Prediction in ROP, OA, and Breast Density

A summary table detailing the size and training/validation/test splits for three datasets used in a medical imaging study. The datasets focus on predicting disease severity in retinopathy of prematurity (ROP) and knee osteoarthritis (OA), and breast density. The 5.5 KB Excel file was authored by Katharina V. Hoebel and last updated in April 2026.

Use Cases

• Benchmarking model performance based on dataset splits
• Planning training strategies based on dataset size information
• Comparing dataset composition across three different medical imaging tasks

Strengths

• Dataset splits are explicitly documented, which aids in reproducibility
• The file is small (5.5 KB), facilitating quick download and inspection
• The data is associated with a specific, published medical imaging study

Limitations

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

Provenance

Source

figshare

Freshness

Last updated 2026-04-17 17:54:56; freshness should be verified