PathoCell: A Benchmark for Pathology Foundation Models

A benchmark suite for evaluating cell phenotyping capabilities of pathology Foundation Models, created by Kainmueller-Lab and last updated on 2025-10-09. The collection includes four key datasets processed into the LMDB format to facilitate large-scale experimentation. The datasets are hosted on the Hugging Face platform.

Use Cases

• Benchmarking pathology foundation models based on cell phenotyping capabilities
• Training models for computational pathology using the provided LMDB-formatted datasets
• Evaluating model performance on a standardized suite of pathology tasks

Strengths

• Includes four distinct datasets for comprehensive benchmarking
• Data is processed into the efficient LMDB format for large-scale use

Limitations

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

Provenance

Source

Kainmueller-Lab

Collection Method

Benchmark datasets for computational pathology, likely curated from research sources.

Time Range

null

Freshness

Last updated 2025-10-09 15:32:49

Geography

null