The browser you are using is not supported by this website. All versions of Internet Explorer are no longer supported, either by us or Microsoft (read more here: https://www.microsoft.com/en-us/microsoft-365/windows/end-of-ie-support).

Please use a modern browser to fully experience our website, such as the newest versions of Edge, Chrome, Firefox or Safari etc.

Artificial intelligence in breast imaging

With a unique database of images we are investigating the use of artificial intelligence in breast imaging.

Progress in Artificial Intelligence – AI – is rapid in many medical fields. In breast imaging, AI has mainly been used to improve CAD – computer assisted detection. Traditional CAD indicates suspicious areas on the mammogram, but is ineffective in screening as excessive marks distract readers when little more than 0.5% of women have cancer. New AI CAD algorithms based on machine learning perform better. Standalone performance comparable or superior to that of trained breast radiologists has been reported, though relatively few if any studies have evaluated how it would perform in actual clinical practice using unenriched screening data. With a high quality, unique database of mammography and breast tomosynthesis images we are conducing such research, investigating how AI would perform in different clinical scenarios.

Two people watching a screen where mammography images are displayed. Photo