Prediction Probabilities for CNN Models on Peritoneal Metastasis Test Set

Chao Zhang published a table of prediction probabilities from classical convolutional neural network models for peritoneal metastasis on a test set. The data compares model performance at dropout probabilities of 0 and 0.3. The dataset is 35.4 KB in size and was last updated on May 14, 2026.

Use Cases

• Compare model performance across different CNN architectures based on the prediction probabilities.
• Analyze the impact of dropout regularization on model confidence for medical image classification.
• Benchmark classical CNN models for the task of peritoneal metastasis detection.

Strengths

• Dataset provides a direct comparison of model predictions at two specific dropout probabilities (0 and 0.3).
• File size is small (35.4 KB), facilitating quick download and inspection.

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

Chao Zhang via figshare

Collection Method

Likely contains outputs from evaluating trained CNN models on a held-out test set.

Freshness

Last updated 2026-05-14 17:44:25; freshness should be verified.