{"url":"/dataset/tcga","name":"TCGA","full_name":"The Cancer Genome Atlas","description_markdown":"","description_withheld":null,"homepage":"https://portal.gdc.cancer.gov/","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Medical","url":"/datasets/modality/medical"},{"name":"Tabular","url":"/datasets/modality/tabular"}],"tasks":[{"name":"Classification","url":"/task/classification-1","datasets_with_task":"/datasets/task/classification-1"},{"name":"Multiple Instance Learning","url":"/task/multiple-instance-learning","datasets_with_task":"/datasets/task/multiple-instance-learning"},{"name":"Cancer type classification","url":"/task/cancer-type-classification","datasets_with_task":"/datasets/task/cancer-type-classification"}],"languages":[],"variants":["TCGA"],"data_loaders":[],"num_papers_in_archive":23,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/multiple-instance-learning-on-tcga","task":"Multiple Instance Learning","dataset_variant":"TCGA","rows":8,"metrics":["ACC","AUC"],"first_row_in_archive_order":{"model":"DTFD-MIL (AFS)","paper":"/paper/dtfd-mil-double-tier-feature-distillation","metrics":{"ACC":"0.951"},"code_links":[{"title":"hrzhang1123/dtfd-mil","url":"https://github.com/hrzhang1123/dtfd-mil"},{"title":"liupei101/psemix","url":"https://github.com/liupei101/psemix"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/classification-on-tcga","task":"Classification","dataset_variant":"TCGA","rows":1,"metrics":["AUPRC","AUROC"],"first_row_in_archive_order":{"model":"MSI-H Transformer","paper":"/paper/from-whole-slide-image-to-biomarker","metrics":{"AUPRC":"0.58","AUROC":"0.84"},"code_links":[{"title":"KatherLab/STAMP","url":"https://github.com/KatherLab/STAMP"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/snuffy-efficient-whole-slide-image-classifier","title":"Snuffy: Efficient Whole Slide Image Classifier","date":"2024-08-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/from-whole-slide-image-to-biomarker","title":"From Whole-slide Image to Biomarker Prediction: A Protocol for End-to-End Deep Learning in Computational Pathology","date":"2023-12-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dtfd-mil-double-tier-feature-distillation","title":"DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classification","date":"2022-03-22","rows_on_this_dataset":4,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":2,"samples_unverified":4,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/transmil-transformer-based-correlated","title":"TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification","date":"2021-06-02","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/dual-stream-multiple-instance-learning","title":"Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning","date":"2020-11-17","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":4,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":12,"samples_ran":6,"samples_unverified":6,"pointer_only_for_licence":3,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}