(Press-News.org) 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.
INFORMATION:
E. F. Ohata, G. M. Bezerra, J. V. S. Chagas, A. V. Lira Neto, A. B. Albuquerque, V. H. C. Albuquerque, and P. P. Rebouças Filho, "Automatic detection of COVID-19 infection using chest X-ray images through transfer learning," IEEE/CAA J. Autom. Sinica, vol. 8, no. 1, pp. 239-248, Jan. 2021.
Fulltext is available:
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9205687
IEEE/CAA Journal of Automatica Sinica aims to publish high-quality, high-interest, far-reaching research achievements globally, and provide an international forum for the presentation of original ideas and recent results related to all aspects of automation.
The first Impact Factor of IEEE/CAA Journal of Automatica Sinica is 5.129, ranking among Top 17% (11/63, SCI Q1) in the category of Automation & Control Systems, according to the latest Journal Citation Reports released by Clarivate Analytics in 2020. In addition, its latest CiteScore is 8.3, and has entered Q1 in all three categories it belongs to (Information System, Control and Systems Engineering, Artificial Intelligence) since 2018.
Why publish with us: Fast and high quality peer review; Simple and effective online submission system; Widest possible global dissemination of your research; Indexed in SCIE, EI, IEEE, Scopus, Inspec. JAS papers can be found at http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=6570654 or http://www.ieee-jas.net
The uneven distribution of school closures in the US since September 2020 threatens to exacerbate regional, racial and class-based divides in educational performance, according to research by Zachary Parolin, of Bocconi University's Department of Social and Political Science, recently published in Nature Human Behavior. For example, in October, only 35% of White students were on distance learning, compared with 52% of Black students, 60% of Hispanic students and 65% of Asian students. And schools recording the lowest math scores were 15% more likely to be closed.
Professor Parolin and Emma Lee (Columbia University) found in fact that exposure ...
Researchers from Queens University, Boston University, University of Toronto, University of Rochester, and Treasury Board Secretariat, Government of Canada published a new paper in the Journal of Marketing that tests a simple, no-cost intervention that can double registration rates, thus helping communities gradually increase the number of prospective donors.
The study, forthcoming in the Journal of Marketing, is titled "Increasing Organ Donor Registrations with Behavioral Interventions: A Field Experiment" and is authored by Nicole Robitaille, Nina Mazar, Claire ...
Scientists at the Institute for Integrated Cell-Material Sciences (iCeMS) and colleagues in Japan have revealed molecular mechanisms involved in eliminating unwanted cells in the body. A nuclear protein fragment released into the cytoplasm activates a plasma membrane protein to display a lipid on the cell surface, signalling other cells to get rid of it. The findings were published in the journal Molecular Cell.
"Every day, ten billion cells die and are engulfed by blood cells called phagocytes. If this didn't happen, dead cells would burst, triggering an auto-immune reaction," explains iCeMS biochemist Jun Suzuki, who led the study. "It is important to understand how dead cells are eliminated as part of our body's maintenance."
Scientists ...
Many tropical cyclone-prone regions of the world are expected to experience storm systems of greater intensity over the coming century, according to a review of research published today in ScienceBrief Review.
Moreover, sea level rise will aggravate coastal flood risk from tropical cyclones and other phenomena, even if the tropical cyclones themselves do not change at all. Models also project an increase in future tropical-cyclone precipitation rates, which could further elevate the risk of flooding.
Researchers at Princeton University, the U.S. National Oceanic and Atmospheric Administration (NOAA), and the University of East Anglia (UEA) examined more than 90 peer-reviewed articles to assess whether human activity is influencing ...
Scientists have identified new genetic clues in people who've had small and often apparently 'silent' strokes that are difficult to treat and a major cause of vascular dementia, according to research funded by the British Heart Foundation (BHF) and published in The Lancet Neurology.
Researchers discovered changes to 12 genetic regions in the DNA of people who have had a lacunar stroke - a type of stroke caused by weakening of the small blood vessels deep within the brain. Over time, damage to the blood vessels and subsequent interruption to blood flow can lead to long-term disability, causing difficulty with thinking, memory, walking and ultimately ...
A pediatric heart transplant procedure pioneered by Canadian doctors--once deemed impossible--has been shown to be at least as effective as the traditional approach, according to END ...
How can we better understand how people move during the pandemic and how they spread COVID-19? New END ...
From microwave ovens to Wi-Fi connections, the radio waves that permeate the environment are not just signals of energy consumed but are also sources of energy themselves. An international team of researchers, led by Huanyu "Larry" Cheng, Dorothy Quiggle Career Development Professor in the Penn State Department of Engineering Science and Mechanics, has developed a way to harvest energy from radio waves to power wearable devices.
The researchers recently published their method inMaterials Today Physics.
According to Cheng, current energy sources for wearable health-monitoring devices have their place in powering sensor devices, but each has its setbacks. Solar power, for example, can only harvest energy when exposed to the sun. A self-powered triboelectric device can only ...
BIRMINGHAM, Ala. - Researchers have found an unexpected synergy between a T-cell stimulatory protein -- the ICOS ligand -- and interleukin-10, an immunoregulatory cytokine, to prevent inflammatory bowel disease in mice. The study will aid the understanding of, and future research into, this immune disorder, which includes Crohn's disease and ulcerative colitis. About 1.6 million Americans have inflammatory bowel disease.
Interleukin-10, or IL-10, was already known as a major player to prevent gut inflammation by establishing and maintaining immune homeostasis in the gut, where it is vital for the host to have a peaceful coexistence with normal intestinal microbes, while the immune system still stands ...
Efforts to shift from petrochemical plastics to renewable and biodegradable plastics have proven tricky -- the production process can require toxic chemicals and is expensive, and the mechanical strength and water stability is often insufficient. But researchers have made a breakthrough, using wood byproducts, that shows promise for producing more durable and sustainable bioplastics.
A study published in Nature Sustainability, co-authored by Yuan Yao, assistant professor of industrial ecology and sustainable systems at Yale School of the Environment (YSE), outlines the process of deconstructing the porous matrix of natural wood into a slurry. The researchers say the resulting material shows ...
