Inception-ResNetV2-SE Model Performance Metrics for Peritoneal Metastasis Prediction

Chao Zhang published a table of sensitivity and specificity metrics for the Inception-ResNetV2-SE model on May 14, 2026. The data shows model performance across different probability thresholds for classifying peritoneal metastasis on a test set. The file is a 12.0 KB XLSX spreadsheet licensed under CC-BY-4.0.

Use Cases

• Selecting an optimal probability threshold for clinical deployment based on the reported sensitivity and specificity trade-off.
• Benchmarking the Inception-ResNetV2-SE model's performance against other diagnostic models for peritoneal metastasis.
• Analyzing the relationship between classification threshold and model performance metrics as described in the data.

Strengths

• Identifies a specific optimal threshold of 0.43 with a sensitivity of 95.5% and specificity of 90.6%.
• Provides combined sensitivity-specificity scores for multiple probability thresholds.
• Dataset is small (12.0 KB) and focused on a single, clearly defined evaluation task.

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 after download.

Provenance

Source

Chao Zhang via figshare

Freshness

Last updated 2026-05-14 17:44:27; freshness should be verified.