{"count":5,"items":[{"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":"open","article":null,"cancer_slugs":["lung-bronchus"],"doi":"10.7937/K9/TCIA.2015.LO9QL9SX","formats":["DICOM","JSON"],"hf":null,"huggingface":null,"kind":"dataset","license":"CC BY 3.0","modalities":["radiology-ct"],"name":"LIDC-IDRI \u2014 Lung Image Database Consortium","page":"/ai-oncology/datasets/lidc-idri","provider":"NCI / TCIA","size":{"items":1018,"notes_en":"nodule annotations by four thoracic radiologists in a two-phase reading","notes_pl":"adnotacje guzk\u00f3w przez czterech radiolog\u00f3w w dwufazowym odczycie","patients":1010,"unit":"CT scans"},"slug":"lidc-idri","summary":"The standard open CT dataset for lung nodule detection and characterisation; basis of the LUNA16 challenge.","tasks":["detection","segmentation","classification"],"url":"https://www.cancerimagingarchive.net/collection/lidc-idri/","verified_at":"2026-09-05T22:25:58.902160"},{"access":"controlled","article":null,"cancer_slugs":["lung-bronchus"],"doi":null,"formats":["DICOM","CSV"],"hf":null,"huggingface":null,"kind":"dataset","license":"NCI CDAS data-use agreement","modalities":["radiology-ct","radiology-xray"],"name":"NLST \u2014 National Lung Screening Trial","page":"/ai-oncology/datasets/nlst","provider":"NCI (Cancer Data Access System)","size":{"notes_en":"randomised trial of low-dose CT vs chest X-ray screening (2002\u20132009) with cancer and mortality follow-up; imaging available for a subset","notes_pl":"randomizowane badanie skriningu niskodawkowym TK vs RTG (2002\u20132009) z obserwacj\u0105 zachorowa\u0144 i zgon\u00f3w; obrazy dost\u0119pne dla podzbioru","patients":53454},"slug":"nlst","summary":"The trial that established LDCT screening; its images plus outcomes trained Sybil and remain the only large public-by-application longitudinal LDCT cohort.","tasks":["risk-prediction","screening","detection"],"url":"https://cdas.cancer.gov/nlst/","verified_at":"2026-09-05T22:25:58.927519"}]}