X-Rays Combined with AI Offer Fast Diagnostic Tool in Detecting COVID-19

X-rays, first used clinically in the late 1890s, could be a leading-edge diagnostic tool for COVID-19 patients with the help of artificial intelligence, according to a team of researchers in Brazil who taught a computer program, through various machine learning methods, to detect COVID-19 in chest X-rays with 95.6 to 98.5% accuracy.

They published their results in IEEE/CAA Journal of Automatica Sinica, a joint publication of the IEEE and the Chinese Association of Automation.

The researchers have previously focused on detecting and classifying lung pathologies, such as fibrosis, emphysema and lung nodules, through medical imaging. Common symptoms presented by suspected COVID-19 infections include respiratory distress, cough and, in more aggressive cases, pneumonia - all visible via medical imaging such as CT scans or X-rays.

"When the COVID-19 pandemic arose, we agreed to put our expertise to use to help deal with this new global problem," said corresponding author Victor Hugo C. de Albuquerque, a researcher in the Laboratory of Image Processing, Signals, and Applied Computing and with the Universidade de Fortaleza.

Many medical facilities have both an inadequate number of tests and lengthy processing times, Albuquerque said, so the research team focused on improving a tool that is readily available at every hospital and already frequently used in diagnosing COVID-19: X-ray devices.

"We decided to investigate if a COVID-19 infection could be automatically detected using X-ray images," Albuquerque said, noting that most X-ray images are available within minutes, compared to the days required for swab or saliva diagnostic tests.

However, the researchers found a lack of publicly available chest X-rays to train their artificial intelligence model to automatically identify the lungs of COVID-19 patients. They had just 194 COVID-19 X-rays and 194 healthy X-rays, while it usually takes thousands of images to thoroughly teach a model to detect and classify a particular target. To compensate, they took a model trained on a large dataset of other X-ray images and trained it to use the same methods to detect lungs likely infected with COVID-19. They used several different machine learning methods, two of which resulted in a 95.6% and a 98.5% accuracy rating, respectively.

"Since X-rays are very fast and cheap, they can help to triage patients in places where the health care system has collapsed or in places that are far from major centers with access to more complex technologies," Albuquerque said. "This approach to detect and classify medical images automatically can assist doctors in identifying, measuring the severity and classifying the disease."

Next, Albuquerque said, the researchers plan to continue testing their method with larger datasets as they become available, with the ultimate goal of developing a free online platform for medical image classification.

E F Ohata, G M Bezerra, J V S Chagas, A V Lira Neto, A B Albuquerque, V H C Albuquerque, P P Rebouças Filho.
Automatic detection of COVID-19 infection using chest X-ray images through transfer learning.
IEEE/CAA J. Autom. Sinica, 2021. doi: 10.1109/JAS.2020.1003393

Most Popular Now

Alcidion Acquires UK Patient Flow Softwa…

Smart health technology provider Alcidion Group has today announced the strategic acquisition of ExtraMed, a UK company which specialises in providing NHS trusts with software that helps frontline staff make...

New AI Tool Tracks Evolution of COVID-19…

A new machine-learning program accurately identifies COVID-19-related conspiracy theories on social media and models how they evolved over time - a tool that could someday help public health officials combat...

Siemens Healthineers Completes Acquisiti…

Siemens Healthineers AG (Frankfurt: SHL) announced that it has successfully completed the acquisition of Varian Medical Systems, Inc. ("Varian"). The acquisition was previously announced on August 2, 2020. "With Varian, Siemens...

Artificial Intelligence Model Predicts w…

The human immune defense is based on the ability of white blood cells to accurately identify disease-causing pathogens and to initiate a defense reaction against them. The immune defense is...

Commission Opens First European Innovati…

Following the launch of the European Innovation Council (EIC) and the announcement of the first funding opportunities, today the Commission opened the first EIC Accelerator calls. The funding worth over...

Talking Health Tech

Opinion Article by Andy Kinnear, Partnerships Director, Ethical Healthcare Consulting. Ethical is different. The guy who founded it, [chief executive] Thomas Webb, comes from an NHS background and he is very...

International Master in Digital Health i…

The Master of Digital Health, MDH (formerly - Master of Medical Informatics, MMI) at European Campus Rottal-Inn (ECRI) - a branch of the Deggendorf University of Applied Sciences (DIT) in Bavaria...

Call for Papers: DigiHealthDay-2021

12 November 2021 The DigiHealthDay 2021 is an International Symposium with the theme "Global Digital Health - Today, Tomorrow, and Beyond". The abstracts pertaining to the field of digital health and...

Proposal for a Regulation Laying Down Ha…

Artificial Intelligence (AI) is a fast evolving family of technologies that can bring a wide array of economic and societal benefits across the entire spectrum of industries and social activities...

Leeds Hospitals go Live with Agfa Health…

Leeds Teaching Hospitals NHS Trust (LTHT) has successfully implemented Agfa HealthCare's Enterprise Imaging (EI) solution, a unified platform complete with clinical tools, reporting and a workflow engine that will help...

Digital Mental Health Interventions for …

An increasing number of digital mental health interventions are designed for adolescents and young people with a range of mental health issues, but the evidence on their effectiveness is mixed...

CoolClinical.com has Developed the First…

Cool Clinical announced the release of the publication on the first Artificial Intelligence system for predicting outcomes of cancer treatment, using data from clinical trials. This is a breakthrough for...