Graph-TCGA-BRCA: Breast Cancer Cell-Graphs for Histopathology

Graph-TCGA-BRCA is a graph-level classification dataset derived from the TCGA-BRCA histopathology dataset. Each 224x224 patch image is converted into a cell-graph where nodes represent detected cell nuclei and edges encode spatial proximity. The dataset was created by author ogutsevda and last updated on 2026-03-03.

Use Cases

• Fine-grained breast lesion subtyping based on cell-graph structure
• Graph-based learning for histopathology based on spatial proximity edges
• Cell morphology and texture analysis based on node features

Strengths

• Derived from the authoritative TCGA-BRCA histopathology dataset
• Converts 224x224 patch images into cell-graphs for graph-based analysis
• Focuses on 2 clinically relevant breast cancer classes

Limitations

• Column-level documentation is absent; field semantics must be inferred after download
• Row count is unknown, which may limit suitability assessment

Provenance

Source

TCGA-BRCA histopathology dataset

Collection Method

Patch images converted into cell-graphs where nodes represent detected cell nuclei and edges encode spatial proximity

Freshness

Last updated 2026-03-03 08:55:11