A custom dataset for pulmonary embolism, likely containing patient and slice-level variations. The dataset appears to be a reduced version of a larger collection, but its exact size and source are unspecified. It was uploaded to Kaggle, but details on the author, organization, and last update are unknown.
Use Cases
- Train machine learning models for pulmonary embolism detection based on patient-level features.
- Analyze variations in embolism presentation across different imaging slices.
- Benchmark model performance on a dataset with inherent patient and slice-level variability.
Strengths
- Focuses on a specific and clinically significant condition, pulmonary embolism.
- Designed to capture variations, which may improve model robustness.
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.