Landmark Localization Performance Metrics for an Additional Dataset

Zhixuan Wei published landmark localization results for an additional dataset on figshare in May 2026. The dataset contains performance indices including median, minimum, maximum, quartiles, and interquartile range errors, with statistical evidence for median error below 0.5 mm. It is a small dataset of 5.5 KB, stored in an XLS file format.

Use Cases

• Benchmarking landmark detection algorithms based on reported error metrics.
• Conducting statistical analysis of model performance using the provided quartiles and interquartile range.
• Validating model precision against a sub-millimeter accuracy threshold based on the reported p-values.

Strengths

• Dataset provides specific statistical performance indices: median, minimum, maximum, Q1, Q3, and IQR.
• Includes p-values for hypothesis testing at the 5% significance level regarding a 0.5 mm error threshold.
• Available under a permissive CC-BY-4.0 license for open use.

Limitations

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

Provenance

Source

Zhixuan Wei via figshare

Freshness

Last updated 2026-05-12 17:46:43; freshness should be verified.