HISTAI-Breast: Histopathology Imaging Linked to Arxiv 2505.12120

HISTAI-breast is a histopathology imaging dataset for breast cancer research released by histai in September 2025. The collection is associated with Arxiv publication 2505.12120 and covers medical samples from the United States. Access is gated and requires manual approval from the authors due to the high resource cost of its assembly.

Use Cases

• Training computer vision models for breast cancer detection using histopathology images
• Benchmarking diagnostic algorithms against the findings in Arxiv 2505.12120
• Analyzing tissue morphology within US-based patient populations

Strengths

• Linked to Arxiv 2505.12120 research
• CC BY-NC 4.0 license for non-commercial research
• Focuses on US-based medical samples

Limitations

• Gated access requiring manual approval from authors
• Public metadata for specific column names and record counts is unavailable

Provenance

Source

histai

Freshness

Last updated September 23, 2025.

Geography

United States