AI tool introduced to grade the severity of a rare cancer
A new study has found that artificial intelligence (AI) is twice as good at analysing the fierceness of a form of cancer than the current system.
Experts from the Royal Marsden Hospital and Institute of Cancer Research have been using a technique called Radiomics to identify signs of retroperitoneal sarcoma – a cancer that develops in the connective tissue of the back of the abdomen – in scans of 170 patients.
An estimated 4,300 people in England are diagnosed with this type of cancer every year.
The new technique, which, is invisible to the naked eye, could replace computerised-tomography (CT) scans.
According to the research, the AI technology was 82% accurate, compared with 44% for lab analysis.
Against this backdrop, researchers are also excited by the idea that AI could be used to diagnose breast cancers and reducing treatment times – the UK government have already warned that this winter will put strain on the NHS.
Dr Paul Huang, from the Institute of Cancer Research in London, said: ‘This kind of technology has the potential to transform the lives of people with sarcoma – enabling personalised treatment plans tailored to the specific biology of their cancer.’
Professor Christina Messiou, who is also from the Institute of Cancer Research, said: ‘We’re incredibly excited by the potential of this state-of-the-art technology. It could lead to patients having better outcomes, through faster diagnosis and more effectively personalised treatment.’
She added that the team hope one day the technology will be used around the globe, with high-risk patients given specific treatment while those at low risk are spared unnecessary treatments and follow-up appointments for scans.
Image: PDPics
NHS has formed an unlikely partnership to promote cancer checks