AI program at Imperial College could improve survival rate of ovarian cancer patients

The breakthrough at Imperial College could improve survival from a disease that kills about 4,300 UK women a year
John Li/Getty Images
Ross Lydall @RossLydall15 February 2019

London researchers have developed an “artificial intelligence” computer program that is up to four times better than doctors at predicting which women are likely to die from ovarian cancer.

The breakthrough at Imperial College paves the way for patients to receive the most effective treatment and could improve survival from a disease that kills about 4,300 UK women a year.

Ovarian cancer is the sixth most common cancer in women, with about 7,300 new cases a year. Survival rates are improving, but two-thirds of women are diagnosed only after it has spread. Only about 35 per cent are alive a decade after diagnosis. Scientists hope that AI could lead to earlier diagnosis of a hard-to-spot cancer.

Lead researcher Professor Eric Aboagye said: “Our technology is able to give clinicians more detailed and accurate information on how patients are likely to respond to different treatments, which could enable them to make better and more targeted treatment decisions.” Published in Nature Communications, the trial at Hammersmith hospital analysed CT scans and tissue samples from 364 women with ovarian cancer from 2004 to 2015.

Software called TEXLab was used to measure the aggressiveness of tumours, based on their structure, shape, size and genetic make-up. Patients were then given a score indicating the severity of the disease.

When the results were compared with blood tests and other measures used by doctors to estimate survival, the software was found to be up to four times more accurate. The researchers hope it can be used to classify patients based on the texture of their cancer, as seen in CT scans, rather than on the type of cancer or how advanced it is.

"Technology is able to give clinicians more detailed and accurate information on how patients are likely to respond to different treatments"

Professor Eric Aboagye

Ovarian cancer is normally diagnosed via a blood test followed by a CT scan. Images are used to determine treatment, which can involve surgery and chemotherapy.

Professor Andrea Rockall, co-author and honorary consultant radiologist at Imperial College Healthcare NHS Trust, said: “Artificial intelligence has the potential to transform the way healthcare is delivered.”

Create a FREE account to continue reading

eros

Registration is a free and easy way to support our journalism.

Join our community where you can: comment on stories; sign up to newsletters; enter competitions and access content on our app.

Your email address

Must be at least 6 characters, include an upper and lower case character and a number

You must be at least 18 years old to create an account

* Required fields

Already have an account? SIGN IN

By clicking Create Account you confirm that your data has been entered correctly and you have read and agree to our Terms of use , Cookie policy and Privacy policy .

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Thank you for registering

Please refresh the page or navigate to another page on the site to be automatically logged in