Washington: Researchers believe that the cutting edge is developing artificial intelligence (AI) that can quickly and accurately identify Lung diseases As Pneumonia And Tuberculosis can relieve the strain on hospitals during the winter months.
Tuberculosis and pneumonia – potentially serious infections that mainly affect the lungs – often require a combination of different diagnostic tests, such as CT scans, blood tests, X-rays and ultrasounds. These tests can be expensive, with often long wait times for results.
Developed by UWS, the revolutionary technology – originally designed to rapidly detect Covid-19 from X-ray images – has proven to automatically identify a range of different lung diseases within minutes, with around 98 per cent accuracy.
UWS researcher Professor Naeem Ramadan said: “Systems like this could prove crucial to busy medical teams around the world.”
It is hoped that the technology can be used to help relieve the strain on overburdened hospital departments through rapid and accurate detection of disease – freeing up radiographers in constant high demand; reduce waiting time for test results; and creating efficiencies in the testing process.
Professor Ramadan, Director of Effective and Humane Computing for the SMART Environmental Research Center at UWS, led the development of the technology with UWS PhD students Gabriel Okolo and Dr Stamos Katsigiannis.
Professor Ramzan added: “There is no doubt that hospital departments around the world are under pressure and this has been exacerbated by the outbreak of Covid-19, adding more stress to already stressed departments and staff. There is a real need for technology to help alleviate some. This can detect a range of strains and diseases quickly and accurately, helping to free up valuable staff time.
“X-ray imaging is a relatively inexpensive and accessible diagnostic tool that already helps diagnose a variety of conditions, including pneumonia, tuberculosis and Covid-19. Recent advances in AI have made automated diagnosis using chest X-ray scans a very real possibility. . in medical settings.”
The state-of-the-art technique uses X-ray technology, comparing the scans to a database of thousands of images of patients with pneumonia, tuberculosis and Covid. It then uses a process called a deep convolutional neural network – an algorithm commonly used to analyze visual images – to make the diagnosis.
During an extensive testing phase, the technique proved to be 98 percent accurate.
Professor Milan Radosavljevic, Vice-Principal for Research, Innovation and Engagement at UWS, said: “Hospitals around the world are under constant stress. This can be seen across the UK, as our fantastic NHS is under constant pressure, with hard-pressed medical. Impact Enduring staff.
“I am excited about the potential of this innovative technology, which can help streamline diagnostic processes and reduce stress on staff.
“It’s another example of purposeful, impactful research at UWS, as we strive to find solutions to global challenges.”
Researchers at UWS are now exploring the technology’s suitability in detecting other diseases, such as cancer, using X-ray images.
