Medical Datasets Repository This repository offers curated medical datasets for AI/ML research, ensuring easy access and ethical usage to support reproducible healthcare studies. Here are additional repositories you may find useful: Models Repository | Standards Repository
Title
Description
Link
The Cancer Imaging Archive (TCIA)
A large archive of medical images of cancer accessible for public download.
TCIA
OpenNeuro.org
A free and open platform for sharing neuroimaging data.
OpenNeuro
OASIS Brains
Datasets of brain imaging for neurodegenerative diseases.
OASIS Brains
Human Connectome Project
Research data about human brain connectivity.
Human Connectome Project
PathPresenter
Digital pathology images for educational and research purposes.
PathPresenter
CAMELYON Challenges
Datasets for the detection of metastases in lymph node images.
CAMELYON16
CAMELYON17
BioImage Archive
A repository for biological images from various modalities.
BioImage Archive
Medical Decathlon
A collection of medical imaging datasets for training and evaluation.
Medical Decathlon
Physiological Data Datasets
Title
Description
Link
PhysioNet
Resource for complex physiological signals.
PhysioNet
MIMIC-III
A freely accessible critical care database.
MIMIC-III
Government and Institutional Data Repositories
Title
Description
Link
NIH's NIMH Data Archive
A large repository of research data on mental health.
NIMH Data Archive
Healthdata.gov
U.S. government health data.
Healthdata.gov
Data.gov
U.S. government open data.
Data.gov
The World Health Organization
Global health observatory data repository.
WHO
The Human Mortality Database (HMD)
Detailed mortality and population data.
HMD
Data and Tools of the National Center for Health Statistics
Health statistics and data sets.
NCHS Data
OpenFDA
Access to various FDA datasets.
OpenFDA
The US Census Bureau
U.S. population and demographic data.
US Census Bureau
Medical Knowledge and Question Answering Datasets
Title
Description
Link
MedQA (USMLE)
General medical knowledge in US medical licensing exam.
MedQA
PubMedQA
Closed-domain question answering given PubMed abstract.
PubMedQA
MedMCQA
General medical knowledge in Indian medical entrance exams.
MedMCQA
MedRedQA
English consumer Question Answering (QA) dataset containing 51,000 pairs of consumer questions and their corresponding expert answers.
MedRedQA
MultiMedQA (140)
Sample from HealthSearchQA, LiveQA, MedicationQA.
MultiMedQA 140
MMLU-Clinical knowledge
Clinical knowledge multiple-choice questions.
MMLU-Clinical
MMLU Medical genetics
Medical genetics multiple-choice questions.
MMLU-Genetics
MMLU-Anatomy
Anatomy multiple-choice questions.
MMLU-Anatomy
MMLU-Professional medicine
Professional medicine multiple-choice questions.
MMLU-Professional
MMLU-College biology
College biology multiple-choice questions.
MMLU-Biology
MMLU-College medicine
College medicine multiple-choice questions.
MMLU-College
Huggin Face Datasets Kaggle Datasets Mendeley Data
If you need help or have any questions, view contributing guide or feel free to reach out by opening an issue or joining our Discord Community .
Your contributions are invaluable, and together, we can build a healthier future through innovation and excellence in medical AI/ML!