Using artificial intelligence to switch from accident to sagacity in the serendipitous detection of uncommon diseases

Among the acknowledged advantages of artificial intelligence (AI) applications in diagnostic imaging, there is the capability to register apparently hidden features in complex images and to connect them for identifying specific disease patterns. This approach has been effectively applied to established techniques for both diagnostic and prognostic purposes.1 However, the task becomes substantially more demanding if the involved method makes the recognition of subtle changes particularly difficult and its use is mainly finalised to identify coarse abnormalities related to urgent clinical indications.