Pathology Reports Dataset: 44,868 Patient Records and Images

44,868 pathology report images and associated patient data support healthcare AI development. The dataset contains real-world diagnostic findings, specimen descriptions, and pathological observations. InfoBayAI published this collection on Hugging Face, with a last recorded update in June 2026.

Use Cases

• Train information extraction models based on diagnostic findings mentioned in the description.
• Develop document understanding systems based on pathology report images.
• Build clinical decision-support systems based on pathological observations.
• Advance medical NLP research based on the collection of clinical pathology reports.

Strengths

• Contains data from 44,868 patients, providing a substantial sample size.
• Includes 44,868 pathology report images, offering a multimodal resource.
• Comprises real-world clinical reports, likely reflecting diverse diagnostic scenarios.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Last updated 2026-06-03 10:50:23; freshness should be verified.

Provenance

Source

InfoBayAI via Hugging Face

Freshness

2026-06-03 10:50:23