The aim of this narrative review is to take a broader look at the application of Artificial Intelligence (AI), primarily in medical imaging. The authors define basic terms in AI, such as “machine learning” and “deep learning”, as well as provide an analysis on the integration of AI into radiology.
Furthermore, the authors look at the increasing frequency of publications on AI, seeing a growth of 100-150 per year in 2007-2008 to about 700-800 per year in 2016-2017. Finally, the article discusses the future of AI in radiology and healthcare and what this may mean for radiologists working with various AI tools and how they can be utilized for efficiency and value-added tasks.
Key Points:
- Over 10 years, publications on AI in radiology have increased from 100–150 per year to 700–800 per year
- Magnetic resonance imaging and computed tomography are the most involved techniques
- Neuroradiology appears as the most involved subspecialty (accounting for about one-third of the papers), followed by musculoskeletal, cardiovascular, breast, urogenital, lung/thorax, and abdominal radiology (each representing 6–9% of articles)
- Radiologists, the physicians who were on the forefront of the digital era in medicine, can now guide the introduction of AI in healthcare
Authors: Filippo Pesapane, Marina Codari and Francesco Sardanelli