Gallery
Unconditional samples from STREAM, one model per dataset, with no conditioning signal.
Unconditional samples from STREAM trained on 12.2M patches (20×, 256×256) from the breast cancer cohort of The Cancer Genome Atlas (TCGA), TCGA-BRCA9.
Unconditional samples from STREAM trained on 3.4M patches (20×, 256×256) from the colorectal cancer cohort of The Cancer Genome Atlas (TCGA), TCGA-COADREAD10.
Unconditional samples from STREAM trained on 2.7M patches (20×, 256×256) from the skin cohort of SPIDER, an independent non-TCGA dataset, SPIDER-skin11.
The sample list could not be loaded. Serve this folder over HTTP (for example python3 -m http.server) rather than opening the file directly.
References (3)
- 9The Cancer Genome Atlas Network, Comprehensive molecular portraits of human breast tumours, Nature 2012.
- 10The Cancer Genome Atlas Network, Comprehensive molecular characterization of human colon and rectal cancer, Nature 2012. doi:10.1038/nature11252
- 11Nechaev et al., SPIDER: A Comprehensive Multi-Organ Supervised Pathology Dataset and Baseline Models, arXiv preprint 2025. arXiv:2503.02876