An interesting article highlighting some promising results from a study looking at computer aided detection of breast cancer. The article describes that, in the study, an AI model is used to detect breast cancer in mammograms. The study looked at the performance of AI-supported screening (where the scan is first assessed by AI and then by a radiologist) versus the current standard care, and showed a similar rate. Such uses of AI have the potential to reduce burden on medical staff, and so reduce patient waiting times.
Our in-house report looking at AI patent filing trends in Europe has consistently found Life & Medical Sciences to be the technology sector accounting for the largest number of patent filings in the AI space. The European Patent Office's position on the patentability of image processing is also much more favourable than for other AI use cases such as text processing for example. Accordingly, we also see a higher allowance rate for European patent applications classified as computer vision.
As further innovations in this area are developed, it's great to see how increasing application of AI in healthcare can improve patient outcomes.
The trial, published in Lancet Oncology, involved more than 80,000 women from Sweden with an average age of 54.
Half of the scans were assessed by two radiologists, known as standard care, while the other half were assessed by the AI-supported screening tool followed by interpretation by one or two radiologists.
In total, 244 women from AI-supported screening were found to have cancer, compared with 203 women recalled from standard screening.
And the use of AI did not generate more "false positives" - where a scan is incorrectly diagnosed as abnormal.
The false-positive rate was 1.5% in both the AI group and the group assessed by radiologists.
The content of this article is intended to provide a general guide to the subject matter. Specialist advice should be sought about your specific circumstances.
