COVID-19 Posteroanterior Chest X-Ray fused (CPCXR) dataset

Citation Author(s):
Narinder Singh
Research Scholar at Indian Institute of Information Technology Allahabad, India
Professor at Indian Institute of Information Technology Allahabad, India
Submitted by:
Narinder Singh Punn
Last updated:
Tue, 10/27/2020 - 06:38
Data Format:
0 ratings - Please login to submit your rating.


The dataset is genrated by the fusion of three publicly available datasets: COVID-19 cxr image (, Radiological Society of North America (RSNA) (, and U.S.  national  library  of  medicine  (USNLM) collected  Montgomery  country - NLM(MC) ( These datasets were annotated by expert radiologists. The fused dataset consists of samples of diseases labeled as COVID-19, Tuberculosis, Other pneumonia (SARS, MERS, etc.), and Normal. The dataset can be utilized to train and evaulate deep learning and machine learning models as binary and multi-class classification problem.


The main manuscript of the proposed dataset is avaibalble at

The dataset is already split into training, validation and test set. The labels associated with each image is presented in the dedicated *.csv files for each of the sets.

The class distribution and assigned lables in the dataset are as follows: Normal - (0,533), COVID-19 - (1,108), Other pneumonia - (2,515) and Tuberculosis - (3,58)



Submitted by bogdan grumezescu on Thu, 10/29/2020 - 01:46

could u please upload the dataset?

Submitted by Omneya Attallah on Thu, 12/03/2020 - 15:14

upload dataset

Submitted by Madhuri Hiwale on Tue, 05/23/2023 - 01:42