{"count":5,"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":"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":["adult-type-diffuse-gliomas"],"doi":null,"formats":["NIfTI"],"hf":null,"huggingface":null,"kind":"benchmark","license":"challenge terms (registration on Synapse)","modalities":["radiology-mri"],"name":"BraTS \u2014 Brain Tumor Segmentation Challenge","page":"/ai-oncology/datasets/brats","provider":"BraTS organisers (University of Pennsylvania, Indiana University, MICCAI)","size":{"notes_en":"\u22651,250 glioma cases since 2021; later editions add paediatric, metastasis, meningioma and Sub-Saharan Africa tracks","notes_pl":"\u22651250 przypadk\u00f3w glejak\u00f3w od 2021; kolejne edycje dodaj\u0105 \u015bcie\u017cki pediatryczne, przerzut\u00f3w, oponiak\u00f3w i Afryki Subsaharyjskiej","patients":1250,"unit":"multi-parametric MRI cases"},"slug":"brats","summary":"The long-running benchmark for brain tumour segmentation from MRI; nnU-Net-based methods have dominated its leaderboards.","tasks":["segmentation"],"url":"https://www.synapse.org/brats","verified_at":"2026-09-05T22:25:58.886093"},{"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":"open","article":null,"cancer_slugs":["malignant-melanoma","non-melanoma-skin-cancer-nmsc"],"doi":null,"formats":["JPEG","CSV"],"hf":null,"huggingface":null,"kind":"registry","license":"CC-0 / CC BY-NC per contributor","modalities":["dermoscopy"],"name":"ISIC Archive \u2014 International Skin Imaging Collaboration","page":"/ai-oncology/datasets/isic-archive","provider":"ISIC (Memorial Sloan Kettering and partners)","size":{"items":70000,"notes_en":"tens of thousands of images with diagnosis; annual challenge subsets (e.g. 2020: 33,126 images)","notes_pl":"dziesi\u0105tki tysi\u0119cy obraz\u00f3w z rozpoznaniem; coroczne podzbiory konkursowe (np. 2020: 33 126 obraz\u00f3w)","unit":"dermoscopic images"},"slug":"isic-archive","summary":"The public backbone of skin-cancer AI; strongly skewed towards light skin tones, which every model card built on it should say.","tasks":["classification","detection","segmentation"],"url":"https://www.isic-archive.com/","verified_at":"2026-09-05T22:25:58.972520"}]}