Artificial intelligence: what the radiologist should know

Abstract

The application of artificial intelligence is a reality that is common in all parts of modern human life. The term “artificial intelligence” is currently commonly utilized in medical imaging in both the lay and scientific literature to refer to machine learning in general and convolutional neural networks specifically. Key technological developments in machine learning have been completed over the last few years, including improvements in deep learning algorithms, further advances in graphics processing units speed and memory, and the important growth of corporate investment. Deep learning has been widely adopted in image recognition, speech recognition and natural language processing, but is only beginning to impact on healthcare. In radiology, large enthusiasm and, at the same time, huge anxiety are associated with the applications of artificial intelligence and its potential to disrupt the work of the radiologist. Radiologists, who were on the forefront of the digital era in medicine, are in a unique position to welcome the artificial intelligence revolution in health care by virtue of their close relationship with an extraordinary amount of data. In fact, artificial intelligence will offer radiologists new opportunities to take part in patient care both via increased time for consultation but also through developments in imaging and extraction of useful data from those images. On the other hand, there are multifaceted technological, regulatory, and medico-legal obstacles facing the implementation of machine learning in radiology which suggest that efficacious replacement of the radiologist’s work is probably more difficult than is presently imagined by some non-radiologist health care experts and computer science futurists within the next two decades and beyond.

Ähnliche Arbeiten