Abstract

The emergence of COVID-19 as a global pandemic forced researchers worldwide in various disciplines to investigate and propose efficient strategies and/or technologies to prevent COVID-19 from further spreading. One of the main challenges to be overcome is the fast and efficient detection of COVID-19 using deep learning approaches and medical images such as Chest Computed Tomography (CT) and Chest X-ray images. In order to contribute to this challenge, a new dataset was collected in collaboration with “S.E.S Hospital Universitario de Caldas” (https://hospitaldecaldas.com/) from Colombia and organized following the Medical Imaging Data Structure (MIDS) format. The dataset contains 7,307 chest X-ray images divided into 3,077 and 4,230 COVID-19 positive and negative images. Images were subjected to a selection and anonymization process to allow the scientific community to use them freely. Finally, different convolutional neural networks were used to perform technical validation. This dataset contributes to the scientific community by tackling significant limitations regarding data quality and availability for the detection of COVID-19.

Measurement(s)

Radiologic Examination

Technology Type(s)

Artificial Intelligence

Sample Characteristic - Location

Colombia

Details

Title
Cov-caldas: A new COVID-19 chest X-Ray dataset from state of Caldas-Colombia
Author
Alzate-Grisales, Jesús Alejandro 1   VIAFID ORCID Logo  ; Mora-Rubio, Alejandro 1 ; Arteaga-Arteaga, Harold Brayan 1   VIAFID ORCID Logo  ; Bravo-Ortiz, Mario Alejandro 2   VIAFID ORCID Logo  ; Arias-Garzón, Daniel 1 ; López-Murillo, Luis Humberto 1 ; Mercado-Ruiz, Esteban 1 ; Villa-Pulgarin, Juan Pablo 1   VIAFID ORCID Logo  ; Cardona-Morales, Oscar 1 ; Orozco-Arias, Simon 3 ; Buitrago-Carmona, Felipe 3 ; Palancares-Sosa, Maria Jose 4 ; Martínez-Rodríguez, Fernanda 5   VIAFID ORCID Logo  ; Contreras-Ortiz, Sonia H. 6 ; Saborit-Torres, Jose Manuel 7   VIAFID ORCID Logo  ; Montell Serrano, Joaquim Ángel 7 ; Ramirez-Sánchez, María Mónica 8 ; Sierra-Gaber, Mario Alfonso 8 ; Jaramillo-Robledo, Oscar 8 ; de la Iglesia-Vayá, Maria 7 ; Tabares-Soto, Reinel 1 

1  Universidad Autónoma de Manizales, Department of Electronics and Automation, Manizales, Colombia (GRID:grid.441739.c) (ISNI:0000 0004 0486 2919) 
2  Universidad Autónoma de Manizales, Department of Electronics and Automation, Manizales, Colombia (GRID:grid.441739.c) (ISNI:0000 0004 0486 2919); Universidad Autónoma de Manizales, Department of Computer Science, Manizales, Colombia (GRID:grid.441739.c) (ISNI:0000 0004 0486 2919) 
3  Universidad Autónoma de Manizales, Department of Computer Science, Manizales, Colombia (GRID:grid.441739.c) (ISNI:0000 0004 0486 2919); Universidad de Caldas, Department of Systems and Informatics, Manizales, Colombia (GRID:grid.7779.e) (ISNI:0000 0001 2290 6370) 
4  Instituto Politécnico Nacional, Biotechnology Interdisciplinar Professional Unit, Ciudad de México, México (GRID:grid.418275.d) (ISNI:0000 0001 2165 8782) 
5  Universidad de Guadalajara, Department of Translational Bioengineering, Guadalajara, México (GRID:grid.412890.6) (ISNI:0000 0001 2158 0196) 
6  Universidad Tecnológica de Bolívar, School of Engineering, Cartagena de Indias, Colombia (GRID:grid.441684.b) (ISNI:0000 0000 8618 9596) 
7  Unidad Mixta de Imagen Biomédica FISABIO-CIPF. Fundación para el Fomento de la Investigación Sanitario y Biomédica de la Comunidad Valenciana, Valencia, Spain (GRID:grid.428862.2) (ISNI:0000 0004 0506 9859) 
8  S.E.S Hospital Universitario de Caldas, Unidad Imágenes Diagnósticas, Manizales, Colombia (GRID:grid.7779.e) (ISNI:0000 0001 2290 6370) 
Publication year
2022
Publication date
2022
Publisher
Nature Publishing Group
e-ISSN
20524463
Source type
Scholarly Journal
Language of publication
English
DOI
https://doi.org/10.1038/s41597-022-01576-z
ProQuest document ID
2747549695
Copyright
© The Author(s) 2022. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.