Integration of AI in radiography practice: ten priorities for implementation

Artificial intelligence (AI) is a concept coined around the 1950s and so has been around for decades. For different reasons relating to lack of sufficient computational capacity, lack of well curated ‘big data,’ and fragmented understanding of how the brain learns, AI remained the privilege of computer scientists and relevant experts and, despite many promises, did not reach clinical practice, until recently.

With many of the challenges for translation of AI now overcome, it is steadily making its way into medical imaging and radiography practice. Clinical practitioners and researchers alike are investing a lot in this translation from the bench (or perhaps the computer lab, in this case) to the bedside (in radiology).

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