AI outperforms doctors at spotting breast cancer

A new AI programme developed by Google Health, with an international team including researchers from Imperial College London, has been shown to outperform clinical experts when detecting breast cancer in mammograms (in terms of false positives and false negatives).

The programme designed and trained a computer model on X-ray images from nearly 29,000 women. With the NHS already under pressure, these promising initial findings could spell good news the nation’s clinical experts.

In the US, only one radiologist reads the results and the tests are done every one to two years. However, the tests are done every three years in Britain, and each is read by two radiologists (with a third being consulted if there is a disagreement).

Dominic King, UK lead at Google Health, said: “Our team is really proud of these research findings, which suggest that we are on our way to developing a tool that can help clinicians spot breast cancer with greater accuracy.

“Further testing, clinical validation and regulatory approvals are required before this could start making a difference for patients, but we're committed to working with our partners towards this goal.”