DATA

Everything about data including open source, healthcare data sets and more, in one location.

 

MESSIDOR: Methods to Evaluate Segmentation and Indexing Techniques in the field of Retinal Ophthalmology

1200 Retinal image dataset with annotation.

http://www.adcis.net/en/third-party/messidor/

RIGA Dataset :Retinal fundus images for glaucoma analysis

A de-identified dataset of retinal fundus images for glaucoma analysis (RIGA) derived from three sources with 750 original images and 4500 manual marked images

https://deepblue.lib.umich.edu/data/concern/data_sets/3b591905z

High-Resolution Fundus (HRF) Image Database

The public database contains 15 images of healthy patients, 15 images of patients with diabetic retinopathy and 15 images of glaucomatous patients.

https://www5.cs.fau.de/research/data/fundus-images/

DR HAGIS: Diabetic Retinopathy, Hypertension, Age-related macular degeneration and Glacuoma ImageS

39 images for development of vessel extraction algorithms suitable for retinal screening programmes.

https://personalpages.manchester.ac.uk/staff/niall.p.mcloughlin/

 

NSRR Datasets:National Sleep Research Resource

Polysomnography dataset from NSRR for sleep studies.Large collection of deidentified physiologic signals perfect for ML development.

https://sleepdata.org/datasets

NLST Datasets: National Cancer Institute

Datasets from National Cancer Institute of over 54000 patients. They include data on participant characteristics, screening exam results, diagnostic procedures, lung cancer, and mortality. Images from over 75,000 CT screening exams are available. Over 1,200 pathology images from a subset of NLST lung cancer patients (~500 of over 2,000 patients) may be viewed.

https://biometry.nci.nih.gov/cdas/datasets/nlst/

 

The HAM10000 dataset

A large collection of multi-source dermatoscopic images of common pigmented skin lesions containing 10000 images.

https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/DBW86T

Associated publication link below:

The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions

Philipp Tschandl, Cliff Rosendahl & Harald Kittler

 

UCI Machine Learning Repository

This open source repository has more than 400 datasets including healthcare(100+) and non-healthcare ones in searchable and categorized format.

http://archive.ics.uci.edu/ml/datasets.php

Centers for Medicare and Medicaid(CMS) datasets with ResDAC link.

CMS datasets provide US Medicare and Medicaid datasets.

https://data.cms.gov

ResDAC(The Research Data Assistance Center) provides free support to users of CMS datasets.

https://www.resdac.org/learn

Center for disease control(CDC) Datasets

Center for disease control's datasets.Useful for incidence,prevalance of various disorders and mortality data from across the US.

https://data.cdc.gov

 

Healthcare Cost and Utilization Project (HCUP) datasets

Agency for Healthcare Research and Quality's HCUP datasets used to identify, track, and analyze US national trends in health care utilization, access, charges, quality, and outcomes.

https://hcup-us.ahrq.gov/databases.jsp

 

NHS datasets

UK government's National Health services datasets.NHS choices datasets are useful for NLP and sentiment analysis both for GPs and hospitals.

https://data.gov.uk/dataset/73740ffe-cecb-4cba-afb9-51ea996187a1/nhs-england-nhs-choices-hospitals-patient-comments-and-ratings

OASIS Brain MRI dataset

Brain MRI datasets from Open Accesss series of Imaging Studies(OASIS).

http://www.oasis-brains.org/#data

 

OpenNEURO

A free and open platform for sharing MRI, MEG, EEG, iEEG, and ECoG data with over 200 datasets.

https://openneuro.org

 

National Cancer Institute(NCI)-SEER datasets

Cancer epidemiology data available through NCI's Surveillance,Epidemiology and End Result Program(SEER)

https://seer.cancer.gov/data-software/

 

BROAD Institute's Cancer program datasets

Cancer and genomics datasets.

http://portals.broadinstitute.org/cgi-bin/cancer/datasets.cgi

 

MIMIC-CXR

The largest publicly available dataset of de-identified Chest x-rays. 370,000+ chest x-rays with 14 labels in the first version.

Version 2.0 with radiologist text reports and additional data available through link below.

https://physionet.org/content/mimic-cxr/2.0.0/

 

MURA

A dataset of 14,000+ anonymized, radiologist labeled musculoskeletal X-rays from 12,000+ patients from Stanford ML group.

https://stanfordmlgroup.github.io/competitions/mura/

Read their article: https://arxiv.org/abs/1712.06957

 

fastMRI

1500+ knee MRI anonymized dataset from NYU.

https://fastmri.med.nyu.edu