Click below to watch an interview with Sara Hiom from Cancer Research UK
An artificial intelligence programme has been developed which can detect breast cancer from mammograms better than experts, a study has revealed.
New research from a team including Cambridge-based Cancer Research UK has found the AI system gives 1.2 percent fewer incorrect diagnoses (false positives) and 2.7 percent fewer missed cases (false negatives) than radiologists in the UK.
Breast cancer is the most common cancer in the UK - with around 55,000 people diagnosed every year, according to Cancer Research UK.
The programme was developed by Google Health in collaboration with DeepMind, Cancer Research UK, Northwestern University, and Royal Surrey County Hospital.
The team said that the latest study, published in the journal Nature on Wednesday, “set the stage” for the model to potentially support radiologists performing breast cancer screenings.
Currently in the UK, it takes 10 years to train as a radiologist and at least two to assess mammograms.
There are hopes that the system could help with breast cancer diagnoses in the future, but there are no plans for it to be used yet as further testing still needs to take place.
Should the AI come to be used in hospitals, mammograms could be assessed 24-hours a day, but decisions would still be overseen by radiologists.