Artificial intelligence can improve the prognostic accuracy of ovarian cancer tests by a factor of four, British researchers have reported.
The software, developed at Imperial College, London, and the University of Melbourne, Australia, can also help predict the effectiveness of treatments, researchers have reported.
The study suggests that cancers might be classified best according to "subtle" differences in texture found on CT scans, the researchers report in Nature Communications.
The researchers used the software, TEXLab, to analyse tissue samples from 364 women diagnosed with ovarian cancer at Hammersmith Hospital, London, over a period of 11 years.
This generated Radiomic Prognostic Vector scores based on the structure, shape, size and genetic make-up of the tumour.
These proved to be four times as accurate as current tests at predicting patient survival. 5% of patients had high scores and lived for less than two years.
Radiologist Professor Andrea Rockall said: “Artificial intelligence has the potential to transform the way healthcare is delivered and improve patient outcomes. Our software is an example of this and we hope that it can be used as a tool to help clinicians with how to best manage and treat patients with ovarian cancer.”
Fellow researcher Professor Eric Aboagye added: “The long-term survival rates for patients with advanced ovarian cancer are poor despite the advancements made in cancer treatments. There is an urgent need to find new ways to treat the disease.
"Our technology is able to give clinicians more detailed and accurate information on the how patients are likely to respond to different treatments, which could enable them to make better and more targeted treatment decisions.”
Nature Communications 15 February 2019
Leave a Reply