X-Ray Radiology Reports Without Findings from 74,154 Patients

74,154 patient records and 171,040 medical images comprise this collection of X-ray reports without clinical findings. The dataset is designed to support AI development in healthcare and medical imaging, capturing authentic scanner variability and acquisition protocols. It was authored by InfoBayAI and last updated on Hugging Face in June 2026.

Use Cases

• Training medical report generation models based on the clinical narratives and imaging characteristics.
• Developing anomaly detection systems by learning from data labeled as having no findings.
• Benchmarking AI models for medical imaging on a large-scale dataset of X-rays and associated reports.
• Studying scanner variability and acquisition protocols mentioned in the dataset description.

Strengths

• Contains data from 74,154 patients, providing a substantial sample size.
• Includes 171,040 medical images paired with reports.
• Designed to capture authentic imaging characteristics like scanner variability and patient positioning.

Limitations

• 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.
• Row count is unknown, which may limit suitability assessment.

Provenance

Source

InfoBayAI via Hugging Face

Freshness

Last updated 2026-06-02 05:45:45; freshness should be verified.