CAMELYON: Breast Cancer Metastases in Lymph Node Whole-Slide Images

The CAMELYON dataset contains all data for the first computational pathology challenge using whole-slide images. It was created by Radboud University Medical Center to help pathologists identify breast cancer metastases in sentinel lymph nodes. The data is intended to develop AI algorithms that can make this difficult and time-consuming search faster and more accurate.

Use Cases

• Training AI models to detect breast cancer metastases based on whole-slide images of lymph node tissue.
• Benchmarking computer vision algorithms for computational pathology tasks based on the challenge data.
• Developing assistive tools for pathologists to accelerate the review of H&E-stained tissue slides for metastases.

Strengths

• Data originates from a pioneering, first-of-its-kind challenge in computational pathology.
• Dataset is associated with a specific, well-defined medical task: identifying breast cancer metastases in sentinel lymph nodes.
• Released under a permissive CC0-1.0 license, allowing for broad reuse.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count and dataset size are unknown, which may limit suitability assessment.
• Last update date is unknown; freshness unverified.

Provenance

Source

Radboud University Medical Center

Collection Method

Data was gathered for the CAMELYON challenge, likely from clinical pathology workflows.