{"version": "1.0", "generated_at": "2026-07-27T10:47:29.316632+00:00", "total_datasets": 9, "datasets": [{"name": "CheXpert", "url": "https://stanfordmlgroup.github.io/competitions/chexpert/", "description": "224,316 chest radiographs from 65,240 patients. Each report was labeled for the presence of 14 observations as positive, negative, or uncertain.", "category": "medical-images", "modality": "x-ray", "source_repo": "chris-lovejoy/medical-datasets-for-education", "access_type": "open-source", "last_synced": "2026-07-27T10:47:29.316018+00:00"}, {"name": "The National CT Colonography Trial", "url": "https://wiki.cancerimagingarchive.net/pages/viewpage.action?pageId=3539213", "description": "825 cases of CT colonography imaging with accompanying spreadsheets that provide polyp descriptions and their location within the colon segments.", "category": "medical-images", "modality": "ct", "source_repo": "chris-lovejoy/medical-datasets-for-education", "access_type": "open-source", "last_synced": "2026-07-27T10:47:29.316109+00:00"}, {"name": "fastMRI", "url": "https://fastmri.med.nyu.edu", "description": "Several thousand knee MRIs. Requires application for access .", "category": "medical-images", "modality": "mri", "source_repo": "chris-lovejoy/medical-datasets-for-education", "access_type": "registration-required", "last_synced": "2026-07-27T10:47:29.316151+00:00"}, {"name": "Automatic Non-rigid Histological Image Registration (ANHIR) challenge dataset", "url": "https://anhir.grand-challenge.org", "description": "50+ histological sets of whole slide images", "category": "medical-images", "modality": "histology", "source_repo": "chris-lovejoy/medical-datasets-for-education", "access_type": "open-source", "last_synced": "2026-07-27T10:47:29.316188+00:00"}, {"name": "EchoNet-Dynamic", "url": "https://echonet.github.io/dynamic/index.html", "description": "10,030 echocardiogram videos.", "category": "medical-images", "modality": "ultrasound", "source_repo": "chris-lovejoy/medical-datasets-for-education", "access_type": "open-source", "last_synced": "2026-07-27T10:47:29.316220+00:00"}, {"name": "MIMIC-III", "url": "http://physionet.org/physiobank/database/mimic3cdb/", "description": "Anonymized critical care EHR database on 38,597 patients and 53,423 ICU admissions. Requires registration.", "category": "text-data", "modality": "clinical-ehr", "source_repo": "chris-lovejoy/medical-datasets-for-education", "access_type": "registration-required", "last_synced": "2026-07-27T10:47:29.316259+00:00"}, {"name": "S2ORC: The Semantic Scholar Open Research Corpus", "url": "https://github.com/allenai/s2orc#download-instructions", "description": "81.1M English-language academic papers spanning many academic disciplines.", "category": "text-data", "modality": "biomedical-research", "source_repo": "chris-lovejoy/medical-datasets-for-education", "access_type": "open-source", "last_synced": "2026-07-27T10:47:29.316293+00:00"}, {"name": "The Cancer Genome Atlas Program", "url": "https://www.cancer.gov/about-nci/organization/ccg/research/structural-genomics/tcga", "description": "over 2.5 petabytes of genomic, epigenomic, transcriptomic, and proteomic data from over 20,000 primary cancer and matched normal samples spanning 33 cancer types.", "category": "other-modalities", "modality": "bioinformatics", "source_repo": "chris-lovejoy/medical-datasets-for-education", "access_type": "open-source", "last_synced": "2026-07-27T10:47:29.316333+00:00"}, {"name": "Parkinson Speech Dataset", "url": "https://archive.ics.uci.edu/ml/datasets/Parkinson+Speech+Dataset+with++Multiple+Types+of+Sound+Recordings", "description": "26 types of sound recordings taken from 20 Parkinson's patients and 20 health patients.", "category": "other-modalities", "modality": "time-series", "source_repo": "chris-lovejoy/medical-datasets-for-education", "access_type": "open-source", "last_synced": "2026-07-27T10:47:29.316366+00:00"}]}