Harnessing the benefits of AI in the breast imaging pathway

The nature of modern radiology has resulted in extremely large volumes of images stored in local archives. This, combined with advances in computing power and improvements in machine learning techniques, means that AI systems are being developed that are powerful enough to be clinically valuable.

In the UK breast screening programme, image data can be matched with outcome data at an individual level, providing an ideal environment for training AI systems for image classification in the breast screening workflow. This is hailed by some as the answer to the shortage of breast radiologists and provides hope of ensuring greater consistency in the detection of significant abnormalities on mammograms and individual risk stratification. The high priority for policy makers and researchers is reflected in the allocation of two high value NHSX AI awards to companies that have validated algorithms for mammography interpretation.

The content on this page is provided by the individuals concerned and does not represent the views or opinions of RAD Magazine.