Cookies Policy
The website need some cookies and similar means to function. If you permit us, we will use those means to collect data on your visits for aggregated statistics to improve our service. Find out More
Accept Reject
  • Menu

Portuguese researchers developed a tool that allows the automatic analysis of X-rays, in order to assess the evolution of COVID-19 patients

10th December 2020

A team of researchers from the Institute for Systems and Computer Engineering, Technology and Science developed a computer-assisted diagnosis system, in partnership with radiologists from the Vila Nova de Gaia/Espinho hospital centre (CHVNGE) and the Northern Region Health Administration (ARS Norte). This system is able to identify radiological elements of COVID-19 in X-ray images, and it can help defining treatment strategies for each patient, by proposing a second opinion to radiologist or other non-specialised staff, thus supporting their analysis.

"COVID-19 can cause cough, fever and fatigue; in some cases, it can evolve into a severe infection of the airways. Standard chest radiography (X-ray) helps measuring the evolution of the respiratory tract infection and, consequently, determining the each patient's monitoring and treatment strategy. Coronavirus elements can be accurately detected whenever they’re present, which encourages the use of this type of tools to assess the evolution of the disease in patients with mild to severe COVID-19 symptoms", explained Aurélio Campilho, INESC TEC researcher and lecturer at the Faculty of Engineering of the University of Porto (FEUP).

The algorithm developed by INESC TEC is based on deep learning methods. The system automatically learns the most relevant elements of the image for diagnosis. More specifically, it analyses a significant amount of images representing the different signs of COVID-19, but also images of healthy patients or individuals with other conditions. With enough data, the characteristics of the learned image become representative of a condition, thus enabling the automatic diagnosis.

There are already several studies on the use of support systems for medical diagnosis in these situations, but their clinical applicability is yet to be tested. This project focused on the simulation of the clinical environment, in order to test the developed models. “This validation showed that the system is able to 'learn' directly from the radiologists, thus improving the detection of COVID-19”, mentioned the researcher.

Researchers from INESC TEC, in partnership with radiologists from the Vila Nova de Gaia/Espinho hospital centre (CHVNGE) and the Northern Region Health Administration (ARS Norte), developed the CXR_AI4COVID-19 (Chest Radiography-based AI for Supporting Clinical Decision on COVID-19) project. "This project, in which we combine medicine and engineering, has the potential to generate a useful and powerful diagnosis tool in clinical context. We are currently evaluating the possibility of testing it at CHVNGE, so it can act as a second opinion of easy interpretation, concerning the presence of COVID-19 in X-ray images - thus helping fight against the pandemic”, said Pedro Sousa, radiologist at CHVNGE.

The project lasted for five months and was supported by the RESEARCH4COVID-19 financing line (€29K), promoted by the Foundation for Science and Technology (FCT).

For further inquiries:

Eunice Oliveira

Communication Service


FEUP Campus

Rua Dr Roberto Frias

4200-465 Porto


P +351 22 209 4118

M +351 934 224 331

Porto - December 20, 2020