🎉 Latest News: Our paper on "Vision-Language Transformers in 3D MRI Synthesis" has been accepted at MICCAI 2026!
Home > Datasets > PathoBiomarker-50K Whole Slide Biopsies
Benchmark Dataset 1,017 Accesses

PathoBiomarker-50K Whole Slide Biopsies

License CC-BY-NC 4.0
Data / File Format HDF5 / SVS (450 GB)

Access Dataset & Model Weights

Free for non-commercial academic research under CC-BY-NC 4.0 license terms.

Asset Summary & Description

Multi-center digital pathology corpus containing 50,000 gigapixel whole-slide tissue biopsies with clinical outcome labels.

Data Specifications & Benchmark Metrics

Corpus Details: - 50,000 formalin-fixed paraffin-embedded (FFPE) tissue slides scanned at 40x magnification. - Genomic biomarker annotations (TP53, EGFR, KRAS mutations). - Multi-center data split from 6 international cancer registries.

BibTeX Citation:

@dataset{medvisai_pathobiomarker-50k-whole-slide-biopsies,
  title={ PathoBiomarker-50K Whole Slide Biopsies },
  author={MedVis AI Research Laboratory Team},
  year={2026},
  url={ https://huggingface.co/datasets/medvisai/pathobiomarker-50k }
}

Other Open Datasets & Model Zoo Assets