This dataset consists of chest X-ray images for COVID-19 positive cases along with Normal and Viral Pneumonia images, created by a team of researchers from Qatar University, Doha, Qatar and the University of Dhaka, Bangladesh along with their collaborators from Pakistan and Malaysia in collaboration with medical doctors.
In the current release (as of June 6, 2020), there are 219 COVID-19 positive images, 1341 normal images and 1345 viral pneumonia images.The dataset maintainers continue to update this database as soon as they have new x-ray images for COVID-19 pneumonia patients. Researchers can use this database to produce useful and impactful scholarly work on COVID-19, which can help in tackling this pandemic.
Update Frequency: No set frequency but is updated as soon as new X-ray images are available.
Dataset stats: Total directory size is about 1GB. There are about 2905 .png images ( consisting of 219 COVID-19 positive images, 1341 normal images and 1345 viral pneumonia images).
The database of COVID-19 x-ray images was developed from the Italian Society of Medical and Interventional Radiology (SIRM) COVID-19 DATABASE [1], Novel Corona Virus 2019 Dataset developed by Joseph Paul Cohen and Paul Morrison and Lan Dao in GitHub [2] and images extracted from 43 different publications. References of each image are provided in the metadata. Normal and Viral pneumonia images were adopted from the Chest X-Ray Images (pneumonia) database [3].
-
[1] S.I. S. o. M. a. I. Radiology. (2020). COVID-19 Database. Available: https://www.sirm.org/category/senza-categoria/covid-19/.
-
[2] Joseph Paul Cohen and Paul Morrison and Lan Dao, "COVID-19 image data collection", arXiv:2003.11597, 2020 https://github.com/ieee8023/covid-chestxray-dataset.
-
[3] P. Mooney. (2018). Chest X-Ray Images (Pneumonia). Available: https://www.kaggle.com/paultimothymooney/chest-xray-pneumonia.
The directory size is about 1GB and consists of about 2900 images spread across 3 sub-directories (COVID-19 positive, Normal and Viral Pneumonias). There are metadate excel files for each of the 3 sub-directories.
All the images are in Portable Network Graphics (PNG) file format and resolution is 1024*1024 pixels, which can be easily converted to 224-by-224 or 227-by-227 pixels typically required by the popular Convolutional Neural Networks (CNNs).
Please find the GitHub link for Matlab codes and trained models: https://github.com/tawsifur/COVID-19-Chest-X-ray-Detection.
Please refer to dataset page of more details on the license.
Owner - Tawsifur Rahman
Collaborators: