Intra-reader Agreement for Generated vs Real Delayed-Phase Medical Images

Intra-reader agreement scores between generated and real delayed-phase medical images for detecting abnormalities. The dataset, authored by Changhwan Sung and last updated on May 14, 2026, is stored in a 5.5 KB Excel file. It covers internal and independent validation sets.

Use Cases

• Validate the diagnostic fidelity of synthetic medical images based on reader agreement scores.
• Assess model performance in abnormality detection across internal and independent validation sets.
• Benchmark generative adversarial networks (GANs) or other image synthesis techniques for delayed-phase imaging.

Strengths

• Data is openly licensed under CC-BY-4.0.
• File size is 5.5 KB, indicating a focused, manageable dataset.

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

Changhwan Sung via figshare

Freshness

Last updated 2026-05-14 17:50:27; freshness should be verified.