MIMIC-CXR-10K: A Subset of Chest X-Ray Data in CSV Format

A subset of 10,000 records from the MIMIC-CXR dataset, which is a large publicly available database of chest radiographs. The data is hosted on Kaggle and is likely provided in a CSV format for easier access and analysis. The specific source and time range of this subset are not detailed in the provided metadata.

Use Cases

• Developing models for automated chest X-ray classification (inferred from domain, verify after download)
• Conducting exploratory data analysis on clinical imaging metadata (inferred from domain, verify after download)
• Benchmarking image preprocessing and feature extraction pipelines (inferred from domain, verify after download)

Strengths

• Published on Kaggle, a major platform for data science.
• Derived from the well-known MIMIC-CXR database, suggesting a clinical foundation.

Limitations

• Metadata is minimal; actual content requires verification after download.
• Row count, column definitions, and license information are unknown.
• Data may reflect the biases inherent to the source hospital system and time period of the original MIMIC-CXR collection.

Provenance

Source

MIMIC-CXR database