Artificial Intelligence in Radiology is a hot topic at the moment! So what is Artificial Intelligence?….
Artificial Intelligence– The theory and development of computer systems able to perform tasks normally requiring human intelligence, such as visual perception, speech recognition, decision-making, and translation between languages.
Deep learning– Deep learning is part of a broader family of machine learning methods based on learning data representations, as opposed to task-specific algorithms. Learning can be supervised, semi-supervised or unsupervised.
A huge step forward for radiology is Computer Aided Diagnosis– through image processing, image feature analysis, data classification in deep learning, the possible ability for computers to use images in radiology in order to come to a diagnosis would have a huge effect. It will have the ability to filer out normal plain films and flag abnormal films for review. As well as this it could be used in CTIMRI for example identifying malignancy. A key benefit being, with an increase in the reporting workload of radiologists with hospitals increasingly relying on imaging, artificial intelligence would be a great way to help reduce this.
However developing artificial intelligence requires access to large volumes of data which may be challenging in the UK particularly in the NHS. It also poses a threat to jobs as artificial imaging is likely to be largely driven by computer scientists which will restrict the input of radiologists.
In the UK surrounded already by artificial intelligence in our day to day life we are already ready for it. Now for the next step, we need to promote artificial intelligence amongst the radiology community, including technicians and undergraduates.