{"count":6,"items":[{"access":"open","article":null,"cancer_slugs":["invasive-breast-carcinoma"],"doi":null,"formats":["TIFF","CSV"],"hf":null,"huggingface":null,"kind":"benchmark","license":"CC0","modalities":["histopathology"],"name":"CAMELYON16 / CAMELYON17","page":"/ai-oncology/datasets/camelyon16","provider":"Radboud University Medical Center and partners (grand-challenge.org)","size":{"items":1399,"notes_en":"CAMELYON16: 399 slides (270 train / 129 test) with pixel-level metastasis annotations; CAMELYON17: 1,000 slides from 5 centres with patient-level pN stage","notes_pl":"CAMELYON16: 399 preparat\u00f3w (270 tren. / 129 test.) z adnotacjami przerzut\u00f3w na poziomie pikseli; CAMELYON17: 1000 preparat\u00f3w z 5 o\u015brodk\u00f3w ze stadium pN per pacjent","unit":"WSIs"},"slug":"camelyon16","summary":"The canonical whole-slide benchmark for breast cancer lymph-node metastasis detection; still the first sanity check for any new pathology encoder.","tasks":["detection","classification","segmentation"],"url":"https://camelyon17.grand-challenge.org/","verified_at":"2026-09-05T22:25:58.842206"},{"access":"registration","article":null,"cancer_slugs":["pan-cancer"],"doi":null,"formats":["SVS","MAF","VCF","BAM","TSV","JSON"],"hf":null,"huggingface":null,"kind":"registry","license":"NIH GDS Policy \u2014 open tier; controlled tier via dbGaP","modalities":["genomics","transcriptomics","histopathology","radiology-ct","radiology-mri"],"name":"TCGA \u2014 The Cancer Genome Atlas (via NCI Genomic Data Commons)","page":"/ai-oncology/datasets/tcga","provider":"NCI / NHGRI; hosted by the Genomic Data Commons","size":{"items":30000,"notes_en":"33 cancer types; ~11,000 patients with molecular data; diagnostic slides for most cases; matched clinical follow-up","notes_pl":"33 typy nowotwor\u00f3w; ok. 11 000 pacjent\u00f3w z danymi molekularnymi; preparaty diagnostyczne dla wi\u0119kszo\u015bci przypadk\u00f3w; dopasowana obserwacja kliniczna","patients":11000,"unit":"diagnostic + tissue WSIs"},"slug":"tcga","summary":"The reference multi-omics cancer cohort: molecular profiles, clinical outcomes and whole-slide images for 33 cancer types, downloadable through the GDC portal and API.","tasks":["classification","prognosis","survival-analysis","variant-effect","gene-expression"],"url":"https://portal.gdc.cancer.gov/","verified_at":"2026-09-05T22:25:58.814252"},{"access":"registration","article":null,"cancer_slugs":["pan-cancer"],"doi":null,"formats":["TSV","SVS","DICOM","MAF"],"hf":null,"huggingface":null,"kind":"registry","license":"open (proteomics via PDC) / controlled (raw sequencing via dbGaP)","modalities":["proteomics","genomics","transcriptomics","histopathology","radiology-ct"],"name":"CPTAC \u2014 Clinical Proteomic Tumor Analysis Consortium","page":"/ai-oncology/datasets/cptac","provider":"NCI Office of Cancer Clinical Proteomics Research","size":{"notes_en":"10+ tumour types with proteogenomic profiling (proteome, phosphoproteome) on genomically characterised cases; images in TCIA","notes_pl":"10+ typ\u00f3w guz\u00f3w z profilowaniem proteogenomicznym (proteom, fosfoproteom) na przypadkach scharakteryzowanych genomowo; obrazy w TCIA","patients":1000},"slug":"cptac","summary":"Proteogenomic companion to TCGA: the largest public set where protein-level measurements, genomics and images exist for the same tumours.","tasks":["classification","prognosis","gene-expression"],"url":"https://proteomics.cancer.gov/programs/cptac","verified_at":"2026-09-05T22:25:58.828625"},{"access":"open","article":null,"cancer_slugs":["pan-cancer"],"doi":null,"formats":["DICOM","NIfTI","CSV"],"hf":null,"huggingface":null,"kind":"registry","license":"mostly CC BY 3.0/4.0 per collection; some restricted collections","modalities":["radiology-ct","radiology-mri","pet","mammography","histopathology","radiology-xray"],"name":"TCIA \u2014 The Cancer Imaging Archive","page":"/ai-oncology/datasets/tcia","provider":"NCI Cancer Imaging Program; hosted by the University of Arkansas for Medical Sciences","size":{"items":200,"notes_en":"hundreds of collections, tens of thousands of patients; DICOM with linked clinical and sometimes genomic data","notes_pl":"setki kolekcji, dziesi\u0105tki tysi\u0119cy pacjent\u00f3w; DICOM z powi\u0105zanymi danymi klinicznymi, czasem genomowymi","unit":"collections"},"slug":"tcia","summary":"The main public archive of de-identified cancer imaging, organised into collections by disease and modality; the source of most public radiology training data in oncology.","tasks":["segmentation","detection","classification","prognosis"],"url":"https://www.cancerimagingarchive.net/","verified_at":"2026-09-05T22:25:58.836069"},{"access":"registration","article":null,"cancer_slugs":["prostate"],"doi":null,"formats":["TIFF","CSV"],"hf":null,"huggingface":null,"kind":"benchmark","license":"CC BY-NC-SA 4.0 (Kaggle competition rules)","modalities":["histopathology"],"name":"PANDA \u2014 Prostate cANcer graDe Assessment","page":"/ai-oncology/datasets/panda","provider":"Radboud UMC and Karolinska Institutet (Kaggle challenge)","size":{"items":10616,"notes_en":"the largest public prostate biopsy set; Gleason / ISUP grade per biopsy from two centres","notes_pl":"najwi\u0119kszy publiczny zbi\u00f3r biopsji prostaty; stopie\u0144 Gleasona / ISUP per biopsja z dw\u00f3ch o\u015brodk\u00f3w","unit":"biopsy WSIs"},"slug":"panda","summary":"Reference dataset and challenge for AI Gleason grading; the follow-up Nature Medicine paper validated algorithms on external cohorts.","tasks":["classification"],"url":"https://www.kaggle.com/competitions/prostate-cancer-grade-assessment","verified_at":"2026-09-05T22:25:58.872361"},{"access":"open","article":null,"cancer_slugs":["invasive-breast-carcinoma"],"doi":null,"formats":["h5ad","PNG","Parquet"],"hf":{"downloads":3508,"fetched_at":"2026-09-09T21:33:09Z","last_modified":"2024-05-25","license":"cc0-1.0","likes":12},"huggingface":"https://huggingface.co/datasets/1aurent/PatchCamelyon","kind":"benchmark","license":"CC0","modalities":["histopathology"],"name":"PatchCamelyon (PCam)","page":"/ai-oncology/datasets/patchcamelyon","provider":"Veeling et al.; mirrored on Hugging Face","size":{"items":327680,"notes_en":"derived from CAMELYON16; binary label = tumour tissue in the central 32\u00d732 region","notes_pl":"pochodna CAMELYON16; etykieta binarna = tkanka guza w centralnym obszarze 32\u00d732","unit":"96\u00d796 patches"},"slug":"patchcamelyon","summary":"Small, fast, fully open patch-classification benchmark \u2014 the standard smoke test for image encoders in pathology and a common zero-shot evaluation set.","tasks":["classification"],"url":"https://github.com/basveeling/pcam","verified_at":"2026-09-05T22:25:58.858045"}]}